© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197439
    Prev
    Next
    INDEX
    Explanations

    abstract expressionism

    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_15_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
    е
    0.60
    ز
    0.59
     در
    0.59
     с
    0.58
     eighty
    0.58
    ش
    0.57
     S
    0.55
     د
    0.54
    да
    0.52
     Y
    0.51
    POSITIVE LOGITS
    javac
    0.60
     geolocation
    0.59
     javac
    0.58
     mute
    0.54
    াইব
    0.54
     proizvođa
    0.53
    gios
    0.52
    Kost
    0.52
    liefer
    0.52
     leak
    0.51
    Activations Density 0.000%

    No Known Activations