© 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. 59208
    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
    a
    1.81
    া
    1.77
    in
    1.63
    も
    1.53
    า
    1.52
    在
    1.46
    し
    1.44
    い
    1.42
    ও
    1.38
    ه
    1.34
    POSITIVE LOGITS
     of
    1.06
    ns
    1.06
    ningar
    1.06
    ni
    1.05
    ong
    1.04
    ning
    1.03
    reng
    1.02
    ren
    0.98
    bted
    0.98
    ög
    0.97
    Activations Density 0.000%

    No Known Activations