© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2220
    Prev
    Next
    INDEX
    Explanations

    phrases that express an opinion or judgement

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating perception or opinion

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

    opinions and impressions

    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
     الحره
    -0.65
    ValueGeneration
    -0.59
     tartalomajánló
    -0.59
    öße
    -0.57
     offence
    -0.57
     offense
    -0.55
     MANT
    -0.54
     ModelExpression
    -0.54
    cologist
    -0.54
     getArguments
    -0.54
    POSITIVE LOGITS
    contentLoaded
    0.69
    MLLoader
    0.58
    ⓧ
    0.53
    Citiți
    0.53
     stronger
    0.50
     PLWABN
    0.48
     rhestr
    0.47
     reluctant
    0.46
     indisponible
    0.46
     unable
    0.45
    Activations Density 0.910%

    No Known Activations