© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52897
    Prev
    Next
    INDEX
    Explanations

    *args, **kwargs

    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_31_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
    von
    0.43
     Rot
    0.43
     Joh
    0.43
    ibs
    0.42
    X
    0.41
     New
    0.41
     Our
    0.40
    Tx
    0.40
     Tx
    0.40
     Bo
    0.39
    POSITIVE LOGITS
     millennia
    0.41
    пропетров
    0.41
     कंपनियां
    0.38
     calendriers
    0.37
     jeopardize
    0.37
     maintenant
    0.37
    燜
    0.37
     кле
    0.36
    aziland
    0.36
     thicken
    0.36
    Activations Density 0.001%

    No Known Activations