© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120857
    Prev
    Next
    INDEX
    Explanations

    painting, doors, block

    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_38_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
     eszk
    0.41
     forwarding
    0.37
    剣
    0.37
    HasFieldError
    0.36
    Duke
    0.36
    Twe
    0.35
    Tend
    0.35
    τρ
    0.34
     Tweets
    0.34
     spot
    0.34
    POSITIVE LOGITS
    楼
    0.44
    樓
    0.42
     binary
    0.40
    ミノ
    0.38
     polo
    0.38
    atibus
    0.38
     متا
    0.38
    repet
    0.38
    hati
    0.37
    binary
    0.37
    Activations Density 0.000%

    No Known Activations