© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39378
    Prev
    Next
    INDEX
    Explanations

    select object or group

    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
    h
    1.06
    ار
    0.89
    f
    0.84
    ر
    0.78
    us
    0.77
    id
    0.76
    ol
    0.76
    hv
    0.73
    ad
    0.71
    olak
    0.71
    POSITIVE LOGITS
    ’
    0.83
    INGS
    0.74
    EM
    0.66
    Select
    0.66
    Have
    0.64
    ERS
    0.62
    EV
    0.62
     godina
    0.60
    运转
    0.60
    Audio
    0.60
    Activations Density 0.010%

    No Known Activations