© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4649
    Prev
    Next
    INDEX
    Explanations

    Missing children

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ➎
    0.48
    ❺
    0.47
    romeda
    0.41
    irmi
    0.39
    fifth
    0.39
    ⑤
    0.38
    move
    0.37
     五
    0.36
     BLUE
    0.36
     Berman
    0.36
    POSITIVE LOGITS
     ascorbic
    0.40
    <0x91>
    0.39
    ibc
    0.38
    COc
    0.37
     lauf
    0.37
    kelijke
    0.36
    ючи
    0.35
    克力
    0.35
     अफेयर्स
    0.35
     gl
    0.35
    Activations Density 0.013%

    No Known Activations