© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58330
    Prev
    Next
    INDEX
    Explanations

    adders and related circuits

    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_2_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
    <0x80>
    1.15
     вас
    0.97
     уви
    0.93
    জ
    0.89
    you
    0.88
    \,
    0.86
    {
    0.86
    _
    0.84
     és
    0.84
     vestiges
    0.84
    POSITIVE LOGITS
    ர்
    1.20
    li
    1.12
    s
    1.11
    ול
    1.02
    ن
    1.00
    ний
    0.99
    ोल
    0.99
    ر
    0.98
    सी
    0.97
    ों
    0.96
    Activations Density 0.000%

    No Known Activations