© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130213
    Prev
    Next
    INDEX
    Explanations

    teen, appa, son, hunger, rich, fashion

    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_6_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
    v
    0.61
    al
    0.61
    b
    0.59
    n
    0.58
    c
    0.57
    t
    0.54
    -
    0.54
    p
    0.52
    w
    0.52
    h
    0.49
    POSITIVE LOGITS
     vremena
    0.45
     كلمات
    0.45
    。
    0.44
    antwoord
    0.44
     تاريخ
    0.44
    да
    0.43
     الدكتور
    0.42
    <0xF3>
    0.42
     حيات
    0.42
     কেননা
    0.42
    Activations Density 0.000%

    No Known Activations