© 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. 6552
    Prev
    Next
    INDEX
    Explanations

    file paths and code related to Python's Django framework.

    oai_token-act-pair · gemini-2.0-flash

    code and configuration files

    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
     (
    -0.52
     $(
    -0.46
    (
    -0.44
    W
    -0.43
    }(
    -0.43
     }(
    -0.43
    com
    -0.42
     }(\
    -0.42
    $(
    -0.41
    ~(
    -0.41
    POSITIVE LOGITS
    ReusableCell
    0.93
    aarrggbb
    0.85
    mybatisplus
    0.83
    ContentAsync
    0.83
     nakalista
    0.83
    RenderAtEndOf
    0.83
    AndEndTag
    0.82
    TagMode
    0.79
    AsUp
    0.78
    TagHelper
    0.75
    Activations Density 7.921%

    No Known Activations