© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205335
    Prev
    Next
    INDEX
    Explanations

    It

    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_56_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
    Making
    0.47
    making
    0.41
     tie
    0.40
     Making
    0.40
     making
    0.39
    逝
    0.39
    Unser
    0.39
    Fitting
    0.39
    Tie
    0.37
     Tahoma
    0.36
    POSITIVE LOGITS
     sense
    0.73
     Sense
    0.68
    sense
    0.63
    Sense
    0.62
    감
    0.61
     sentido
    0.60
     senso
    0.54
    感
    0.54
    feels
    0.51
    感を
    0.51
    Activations Density 0.005%

    No Known Activations