© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10553
    Prev
    Next
    INDEX
    Explanations

    phrases with the word 'up' and some prepositions like 'in', 'on', 'to' and pronouns like 'me', 'my' along with associated verbs.

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating outcomes or results

    np_token-act-pair-logits · gpt-4o-mini

    up/himself/herself

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主に
    -0.50
     exercí
    -0.49
    __((
    -0.48
     كومونز
    -0.47
     yaklaş
    -0.46
    بوابة
    -0.45
     nostru
    -0.45
    ()][
    -0.44
    **)
    -0.44
    usiai
    -0.44
    POSITIVE LOGITS
     with
    0.73
    IContainer
    0.71
     discovering
    0.62
     realizing
    0.60
     returning
    0.60
     responding
    0.59
     replacing
    0.58
    <bos>
    0.58
    iented
    0.57
     AssemblyCulture
    0.57
    Activations Density 4.675%

    No Known Activations