© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8319
    Prev
    Next
    INDEX
    Explanations

    the word "auto" or prefixes with "auto-".

    oai_token-act-pair · gemini-2.0-flash

    auto

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     tartalomajánló
    -0.89
    PerformLayout
    -0.84
    
    -0.79
     myſelf
    -0.79
     ―――――
    -0.78
    principalColumn
    -0.75
    InputBorder
    -0.73
    AndEndTag
    -0.73
     EnglishChoose
    -0.72
     ―――
    -0.72
    POSITIVE LOGITS
    corn
    0.39
    carrier
    0.39
    AuthGuard
    0.38
    down
    0.36
    bar
    0.35
     cenar
    0.35
     Lexikon
    0.34
    trade
    0.34
    avits
    0.34
    trading
    0.34
    Activations Density 1.152%

    No Known Activations