© 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. 42378
    Prev
    Next
    INDEX
    Explanations

    voice actor or voice box

    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
    thrombin
    0.71
    ਭ
    0.66
    ভাই
    0.65
    throw
    0.64
    as
    0.64
    φα
    0.63
    with
    0.63
    ்ட்
    0.63
    براین
    0.63
    prend
    0.62
    POSITIVE LOGITS
    0.68
    。
    0.60
    ę
    0.59
    ă
    0.58
    ANG
    0.57
     besteht
    0.57
    S
    0.57
    ও
    0.57
    Ě
    0.56
    lık
    0.56
    Activations Density 0.006%

    No Known Activations