© 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. 11972
    Prev
    Next
    INDEX
    Explanations

    segmented text, possibly signatures or code snippets

    oai_token-act-pair · gemini-2.0-flash

    internet comments

    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
    )}</
    -0.62
    "]]
    -0.60
    QMetaType
    -0.59
    cplusplus
    -0.57
    انيف
    -0.56
    ,:);
    -0.56
    providedIn
    -0.56
    "]}
    -0.55
    ]--;
    -0.55
    "}},
    -0.53
    POSITIVE LOGITS
    -
    0.69
    m
    0.56
    +#+
    0.56
    sco
    0.55
     transfieras
    0.54
    j
    0.53
    anne
    0.52
    gy
    0.50
    sko
    0.50
     Sco
    0.49
    Activations Density 15.544%

    No Known Activations