© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9265
    Prev
    Next
    INDEX
    Explanations

    code and technical

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     عل
    0.76
     మ
    0.73
     przy
    0.73
     مع
    0.73
     ಸ
    0.71
     ರ
    0.70
     keyboard
    0.67
     এক
    0.67
     ტ
    0.66
     при
    0.66
    POSITIVE LOGITS
    appel
    0.77
     AFFAIRS
    0.69
    Mobile
    0.68
     පිළිබ
    0.68
    inspector
    0.67
    Frag
    0.67
    Normally
    0.66
    ="(
    0.66
     INSPE
    0.65
    )(
    0.65
    Activations Density 1.304%

    No Known Activations