© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44501
    Prev
    Next
    INDEX
    Explanations

    Danbooru, Quayle, Minimisation

    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_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
    ين
    0.76
     ene
    0.71
    a
    0.67
     algo
    0.63
    ");
    0.61
     utile
    0.61
     adev
    0.61
     sua
    0.60
     luch
    0.60
    کول
    0.59
    POSITIVE LOGITS
    I
    0.92
    (
    0.77
    0
    0.73
    8
    0.64
    6
    0.63
    ،
    0.58
    Operation
    0.54
    itzen
    0.54
    9
    0.54
    Fle
    0.54
    Activations Density 0.004%

    No Known Activations