© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15191
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an evaluative or comparative statement

    oai_token-act-pair · gemini-2.0-flash

    danger

    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
    Portály
    -0.59
    GEBURTSDATUM
    -0.58
    Przypisy
    -0.58
    서는
    -0.57
    ResumeLayout
    -0.56
    isContained
    -0.49
    EndContext
    -0.47
     transfieras
    -0.46
    creativecommons
    -0.46
    aj
    -0.46
    POSITIVE LOGITS
     error
    1.51
     risk
    1.47
    error
    1.38
    risk
    1.30
     danger
    1.20
     conflict
    1.16
    Risk
    1.15
     threat
    1.14
     Risk
    1.13
    Error
    1.12
    Activations Density 8.366%

    No Known Activations