© 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. 943
    Prev
    Next
    INDEX
    Explanations

    words that commonly occur in sports reporting on fighting or wrestling

    oai_token-act-pair · gemini-2.0-flash

    Concatenated text passages

    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
    MessageOf
    -0.50
    Accessors
    -0.49
    lardır
    -0.47
    Referensi
    -0.47
    ccin
    -0.45
    ();
    -0.45
     HAROLD
    -0.44
    FAS
    -0.44
    ')):
    -0.44
    ="<?
    -0.43
    POSITIVE LOGITS
    styleType
    0.65
    ⓧ
    0.61
    bootstrapcdn
    0.61
    ailles
    0.57
    MLLoader
    0.57
    ChildScrollView
    0.55
    Jeografia
    0.54
     незавершена
    0.52
    abuse
    0.52
    scriptcase
    0.51
    Activations Density 1.457%

    No Known Activations