© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16087
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gemini-2.0-flash

    names and places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    yntaxException
    -0.60
    +#+#
    -0.54
    @[+][
    -0.47
    twimg
    -0.46
     Roskov
    -0.46
    copg
    -0.43
    <?
    -0.43
    DataContract
    -0.42
    Obrázky
    -0.42
    writeFieldEnd
    -0.41
    POSITIVE LOGITS
     Ellison
    0.75
    DEL
    0.75
     Helle
    0.74
    Ell
    0.72
     Jel
    0.72
     TAL
    0.69
     HEL
    0.69
     ELL
    0.68
    kel
    0.68
    alli
    0.68
    Activations Density 10.822%

    No Known Activations