© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    protocols and minutes

    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
    على
    2.92
     advertised
    2.66
    욱
    2.61
    ˜
    2.61
     bestimmt
    2.56
     значит
    2.54
    believe
    2.50
     prominently
    2.47
     peces
    2.47
    |^{
    2.42
    POSITIVE LOGITS
    т
    2.96
    ую
    2.86
    е
    2.73
    ाइवेट
    2.71
    ス
    2.61
    heastern
    2.60
    濘
    2.59
    ﾞ
    2.53
    ীকরণ
    2.52
    事
    2.50
    Activations Density 0.034%

    No Known Activations