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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8462
    Prev
    Next
    INDEX
    Explanations

    references to unintelligent people and deceptive practices

    oai_token-act-pair · gemini-2.0-flash

    foolishness

    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
     dumb
    -1.70
     stupid
    -1.54
    dumb
    -1.51
     Stupid
    -1.48
     idiot
    -1.46
     foolish
    -1.44
     stupidity
    -1.43
     fools
    -1.41
     ignorant
    -1.40
     Idiot
    -1.38
    POSITIVE LOGITS
    nessed
    0.56
    ثيق
    0.52
    writeFieldEnd
    0.51
    HttpDelete
    0.50
    canestro
    0.47
    ppé
    0.46
    jaro
    0.46
     مث
    0.46
    mack
    0.46
     perle
    0.46
    Activations Density 2.431%

    No Known Activations