© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12352
    Prev
    Next
    INDEX
    Explanations

    words with shared suffixes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ,
    -0.67
     
    -0.53
    /
    -0.52
     с
    -0.52
     x
    -0.51
     (
    -0.50
     at
    -0.50
     or
    -0.50
     "
    -0.48
    ;
    -0.47
    POSITIVE LOGITS
     itſelf
    1.07
    ^(@)
    1.00
    ")));
    0.99
     Efq
    0.99
     myſelf
    0.98
    })));
    0.98
     $_"
    0.96
    ՚
    0.94
    )");
    0.94
     raiſ
    0.91
    Activations Density 1.305%

    No Known Activations