© 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. 289
    Prev
    Next
    INDEX
    Explanations

    I am not able to determine what Neuron 4 is looking for; its activations are too varied to identify a pattern

    oai_token-act-pair · gemini-2.0-flash

    Foreign language fragments

    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
     Soma
    -0.73
     SBS
    -0.71
    SBS
    -0.68
     SIS
    -0.68
     Sos
    -0.68
     SST
    -0.66
     SSA
    -0.66
     SOT
    -0.66
     SSP
    -0.66
     SSE
    -0.65
    POSITIVE LOGITS
    AllowUser
    0.48
    kuper
    0.46
    opla
    0.45
     Fuhr
    0.45
    팩
    0.45
    ToFit
    0.45
     ufficio
    0.45
    انجليز
    0.44
    gas
    0.44
    uez
    0.44
    Activations Density 0.803%

    No Known Activations