© 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. 10340
    Prev
    Next
    INDEX
    Explanations

    descriptions of how things are affected by something

    oai_token-act-pair · gemini-2.0-flash

    negatively affected

    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
     affected
    -1.45
     affecting
    -1.45
     Affected
    -1.43
    Affected
    -1.41
     affect
    -1.40
     affects
    -1.37
     impacted
    -1.34
    affect
    -1.34
     Affecting
    -1.32
     Affect
    -1.29
    POSITIVE LOGITS
    igshid
    0.67
     الدولى
    0.56
    ństw
    0.56
     fielding
    0.54
     Imp
    0.52
    urlencoded
    0.52
    Unmarshal
    0.52
     reservados
    0.51
     expédié
    0.50
    Imp
    0.49
    Activations Density 3.284%

    No Known Activations