© 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. 6082
    Prev
    Next
    INDEX
    Explanations

    code with high indentation and a specific code structure

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    الحياه
    -0.85
    protoimpl
    -0.69
    WithIOException
    -0.66
    IndentedString
    -0.63
    stylers
    -0.63
     समीक्षाओं
    -0.60
    Diweddarwch
    -0.59
    queryInterface
    -0.57
     himo
    -0.57
     PhpStorm
    -0.56
    POSITIVE LOGITS
    mtable
    0.59
    ">)</
    0.53
    __))
    0.51
    $~
    0.51
     للمعارف
    0.51
    ssal
    0.50
    }}_
    0.50
    )}_
    0.48
    aval
    0.48
    TagMode
    0.48
    Activations Density 4.034%

    No Known Activations