© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 40334
    Prev
    Next
    INDEX
    Explanations

    locations and outdoor activities

    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_11_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
    ي
    0.13
    es
    0.13
    in
    0.12
    p
    0.11
    i
    0.10
    o
    0.10
    j
    0.10
    c
    0.10
    ge
    0.10
    jg
    0.09
    POSITIVE LOGITS
    తాయి
    0.09
    Cook
    0.09
     Concert
    0.09
     Reduced
    0.09
     अमेरिका
    0.09
     रविवार
    0.08
    Φ
    0.08
     Config
    0.08
    U
    0.08
    ánchez
    0.08
    Activations Density 0.009%

    No Known Activations