© 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. 202383
    Prev
    Next
    INDEX
    Explanations

    stick / sticks

    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
    णीय
    0.39
     चीफ
    0.38
     pulsations
    0.38
     benc
    0.37
    chnen
    0.37
    atemala
    0.37
    tal
    0.37
    奏
    0.37
    aniyati
    0.36
    ামত
    0.36
    POSITIVE LOGITS
     sticks
    0.44
     fastest
    0.42
     stick
    0.41
     PR
    0.41
    stick
    0.40
     slog
    0.40
    PR
    0.39
    ラグ
    0.39
     Parti
    0.39
    sticks
    0.37
    Activations Density 0.000%

    No Known Activations