© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202981
    Prev
    Next
    INDEX
    Explanations

    make

    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_46_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
     Worse
    0.44
     worst
    0.42
    력
    0.41
     worse
    0.40
     hvert
    0.39
    Worst
    0.38
     JSONObject
    0.38
    력을
    0.38
     Theology
    0.38
    νος
    0.37
    POSITIVE LOGITS
    Charlie
    0.44
    make
    0.41
    Make
    0.41
    さない
    0.41
    ோர
    0.40
    沥
    0.40
     disgu
    0.39
     சாப்பிட
    0.39
    maked
    0.38
     inspiración
    0.38
    Activations Density 0.003%

    No Known Activations