© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    modelmodeling physical objects and their details

    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_39_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
     Alkaline
    0.37
    スタル
    0.37
    Anast
    0.35
    IMPLEMENT
    0.35
     Vasil
    0.35
     Stacey
    0.35
    凍
    0.34
    姮
    0.34
     Cruise
    0.33
     Claude
    0.33
    POSITIVE LOGITS
     cabs
    0.44
     assemblies
    0.42
     resin
    0.40
     radiators
    0.37
     flared
    0.36
    鉚
    0.36
     stabilizer
    0.36
     Shaping
    0.36
    恈
    0.36
     modeled
    0.35
    Activations Density 0.044%

    No Known Activations