© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218841
    Prev
    Next
    INDEX
    Explanations

    yr

    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_47_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
    IManager
    0.41
     pernik
    0.39
     Lamar
    0.38
    চৈত
    0.38
    電動
    0.38
     Gilman
    0.38
     --------");
    0.37
     Sejam
    0.37
     Cas
    0.37
    沣
    0.37
    POSITIVE LOGITS
    trans
    0.41
    steigen
    0.40
    mment
    0.39
    lift
    0.38
    helpTool
    0.36
    unud
    0.36
    ue
    0.36
     सुचेता
    0.36
    pixels
    0.36
     ას
    0.36
    Activations Density 0.002%

    No Known Activations