© 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. 8931
    Prev
    Next
    INDEX
    Explanations

    words related to physical objects involved in support and connection

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions

    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
     win
    -0.69
    GraphicsUnit
    -0.58
     متحده
    -0.55
     Win
    -0.55
     Wicidata
    -0.55
     loose
    -0.51
    win
    -0.50
     rejoindre
    -0.50
    Win
    -0.49
    //
    -0.48
    POSITIVE LOGITS
     lenker
    0.62
    GEBURTSDATUM
    0.61
     dig
    0.56
     slope
    0.54
     pro
    0.52
     Winaray
    0.51
    liptic
    0.51
    FieldError
    0.51
     line
    0.50
    ngrx
    0.50
    Activations Density 4.386%

    No Known Activations