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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3247
    Prev
    Next
    INDEX
    Explanations

    words related to electric razors and guitars

    oai_token-act-pair · gemini-2.0-flash

    electricity

    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
     Electric
    -2.33
     electric
    -2.30
    Electric
    -2.25
     ELECTRIC
    -2.16
     electrical
    -2.14
    electric
    -2.13
     Electro
    -2.13
     electro
    -2.09
     Electrical
    -2.05
    Electro
    -2.05
    POSITIVE LOGITS
    ijų
    0.51
     Hays
    0.47
    SizeF
    0.47
     codec
    0.46
     跳转至
    0.45
    verifyException
    0.44
    ConstraintMaker
    0.44
    rès
    0.44
    dAtA
    0.41
    Viungo
    0.41
    Activations Density 2.536%

    No Known Activations