© 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. 157707
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ла
    1.70
    도
    1.40
    も
    1.31
    f
    1.30
    在
    1.28
    ও
    1.20
    -
    1.17
    x
    1.13
    ii
    1.10
    ش
    1.09
    POSITIVE LOGITS
    .
    1.28
    in
    1.19
    ς
    1.16
    inį
    1.12
    inę
    1.10
    ی
    1.09
    s
    0.97
    hā
    0.96
    ۔
    0.96
    ᆞ
    0.96
    Activations Density 0.000%

    No Known Activations