© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9402
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ホン
    0.71
     यूज
    0.66
     says
    0.65
    冏
    0.64
     benef
    0.63
    მის
    0.61
    User
    0.59
     आड
    0.59
    even
    0.58
     Liber
    0.58
    POSITIVE LOGITS
    setVertical
    0.73
     spyware
    0.71
    ഊ
    0.70
    perturb
    0.70
    awi
    0.70
     মাইক্র
    0.69
     ಮೇಲೆ
    0.69
    マイクロ
    0.68
    اموش
    0.68
     enmity
    0.68
    Activations Density 0.000%

    No Known Activations