© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5112
    Prev
    Next
    INDEX
    Explanations

    protecting fingers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
    ago
    0.36
    год
    0.36
     Yuk
    0.35
    ').':
    0.35
     разу
    0.34
    urid
    0.34
    ዑ
    0.34
    ()?>
    0.33
     യൂ
    0.33
     Braga
    0.33
    POSITIVE LOGITS
     finger
    1.63
    Finger
    1.41
     Finger
    1.34
    finger
    1.30
     fingers
    1.22
    指
    1.20
     doigt
    1.15
     dedo
    1.09
     fingert
    1.04
     dedos
    1.03
    Activations Density 0.044%

    No Known Activations