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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8125
    Prev
    Next
    INDEX
    Explanations

    O' names

    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_3_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
    ங்கிணை
    1.91
    iles
    1.84
    ン
    1.82
    TA
    1.81
     pile
    1.79
    дру
    1.74
    aider
    1.73
    𝒖
    1.69
     tage
    1.68
    𝒈
    1.65
    POSITIVE LOGITS
    ../../
    2.12
    ె
    2.11
     breech
    2.09
    ist
    2.03
    e
    2.02
    el
    1.98
     invocation
    1.98
     annexation
    1.96
    습니다
    1.96
     ਇੱਕ
    1.95
    Activations Density 0.001%

    No Known Activations