© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32548
    Prev
    Next
    INDEX
    Explanations

    connect, add, combine, move, place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    é
    0.57
    ки
    0.55
    ai
    0.52
    im
    0.51
    на
    0.51
    al
    0.49
    ang
    0.47
    ين
    0.46
    ون
    0.46
    it
    0.45
    POSITIVE LOGITS
     į
    0.49
     dengan
    0.47
     με
    0.45
     with
    0.44
     līdz
    0.43
     עם
    0.43
     với
    0.43
     procession
    0.43
     junto
    0.42
     σύμφωνα
    0.42
    Activations Density 0.004%

    No Known Activations