© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126705
    Prev
    Next
    INDEX
    Explanations

    presence

    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_37_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
     MyRegisterClass
    0.40
    ၞ
    0.39
    *>(
    0.38
     cools
    0.37
     instantiate
    0.36
    ተት
    0.36
     stmt
    0.35
     maß
    0.35
    '};
    0.35
    ણને
    0.35
    POSITIVE LOGITS
     presence
    2.48
    presence
    2.41
     presencia
    2.36
    Presence
    2.28
     Presence
    2.23
     présence
    2.20
     presença
    2.19
     presenza
    2.13
     присут
    2.03
     حضور
    1.92
    Activations Density 0.021%

    No Known Activations