© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199650
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Derivative
    0.41
    頹
    0.40
     pelang
    0.38
    たる
    0.38
    ান্দ
    0.38
    APB
    0.38
    phthal
    0.38
    没错
    0.37
    胱
    0.37
    Mats
    0.37
    POSITIVE LOGITS
    bert
    0.40
     scoops
    0.39
    ilian
    0.39
    bilical
    0.38
    érien
    0.38
     बैंड
    0.36
     Household
    0.36
    Liens
    0.36
     Herren
    0.35
    BERT
    0.35
    Activations Density 0.001%

    No Known Activations