© 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. 1242
    Prev
    Next
    INDEX
    Explanations

    words expressing strong emotion or opinions, especially negative ones

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    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
     NOT
    -0.88
     NEVER
    -0.86
     ALL
    -0.84
     FREE
    -0.84
     BOTH
    -0.83
     NEW
    -0.81
     ANY
    -0.80
     FOUR
    -0.79
     NONE
    -0.78
     TWO
    -0.77
    POSITIVE LOGITS
     AT
    0.94
    AT
    0.72
     BY
    0.68
     OF
    0.64
     IN
    0.62
     TO
    0.60
     AS
    0.59
    OF
    0.55
     IS
    0.54
    BY
    0.50
    Activations Density 27.670%

    No Known Activations