© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    all sorts of

    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
    Боль
    2.20
    ل
    2.06
    кономи
    1.93
    ٪
    1.89
    আপনার
    1.72
    ح
    1.72
    গরের
    1.71
     outlay
    1.70
    avor
    1.63
    ড
    1.63
    POSITIVE LOGITS
    en
    2.40
    ங்கிணை
    2.27
    ка
    2.18
    س
    2.16
    erate
    2.06
    ी
    2.05
    те
    1.97
    ené
    1.88
    ت
    1.86
    তে
    1.85
    Activations Density 0.012%

    No Known Activations