© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31326
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_31_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
     unpacked
    0.40
     കല
    0.39
     uh
    0.34
    條件
    0.34
     Uhuru
    0.34
    عاية
    0.34
    𝐋
    0.34
     apag
    0.34
    ｱ
    0.34
     rabbi
    0.33
    POSITIVE LOGITS
     இவரது
    0.37
     catchment
    0.36
    空间
    0.36
    bibnamefont
    0.35
     საქართველოს
    0.35
    Bash
    0.34
     Cómo
    0.34
    ຕ້ອງການ
    0.34
    மிய
    0.34
     combien
    0.33
    Activations Density 0.003%

    No Known Activations