© 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. 91472
    Prev
    Next
    INDEX
    Explanations

    ober-/underhitze

    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
    s
    0.87
     País
    0.73
    is
    0.71
    تی
    0.66
    장
    0.62
     TFA
    0.61
    ма
    0.60
    ০০
    0.59
     sứ
    0.59
    त
    0.59
    POSITIVE LOGITS
    have
    0.78
    و
    0.78
     to
    0.78
    ila
    0.66
    vär
    0.65
    vä
    0.64
    urile
    0.63
    obs
    0.63
    ो
    0.63
    ون
    0.62
    Activations Density 0.000%

    No Known Activations