Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4314
    Prev
    Next
    INDEX
    Explanations

    XML/SVG tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fontFamily
    0.50
    ல்
    0.49
    InitTypeDef
    0.46
    د
    0.46
     Ста
    0.45
     lightening
    0.44
    блема
    0.44
    もの
    0.43
     furious
    0.43
    f
    0.43
    POSITIVE LOGITS
    IAMS
    0.63
    Ꮵ
    0.59
    ी
    0.58
     feria
    0.57
    Ꮸ
    0.57
    czych
    0.56
    ো
    0.56
    ᖅ
    0.55
    ië
    0.55
    <unused2125>
    0.55
    Activations Density 0.005%

    No Known Activations