© 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. 226782
    Prev
    Next
    INDEX
    Explanations

    XL ticker symbols

    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
     buildFor
    0.91
    থ
    0.90
     linkCell
    0.89
    ัน
    0.88
     negó
    0.88
    ח
    0.84
    าก
    0.83
    ায়
    0.82
    ת
    0.80
    ONG
    0.80
    POSITIVE LOGITS
    a
    1.64
    h
    1.35
    z
    1.19
    the
    1.16
    ds
    1.15
    dt
    1.15
    g
    1.13
    q
    1.13
    dy
    1.13
    crazy
    1.11
    Activations Density 0.000%

    No Known Activations