© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197265
    Prev
    Next
    INDEX
    Explanations

    zoonotic spillover or earcups

    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_4_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
    at
    0.20
    ა
    0.14
    <0xAA>
    0.14
    <0xAC>
    0.13
    <0x97>
    0.13
     není
    0.13
     букмекерлик
    0.13
    ening
    0.13
    <0xB9>
    0.13
    8
    0.13
    POSITIVE LOGITS
    D
    0.22
    تر
    0.20
    ン
    0.19
    ক
    0.18
    자
    0.18
    ن
    0.17
    マ
    0.17
    '}
    0.17
    ب
    0.17
    G
    0.17
    Activations Density 0.001%

    No Known Activations