© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60840
    Prev
    Next
    INDEX
    Explanations

    second

    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_11_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
     xlabel
    0.36
    inck
    0.36
    ר
    0.33
    豈
    0.33
     Birk
    0.33
     Leslie
    0.32
    ണ്ടും
    0.32
    н
    0.32
    InputDir
    0.32
    р
    0.32
    POSITIVE LOGITS
     ఫ
    0.36
     फ़
    0.34
    apeut
    0.34
    మె
    0.33
    規範
    0.32
     هذه
    0.31
     پس
    0.31
     ファ
    0.31
    бо
    0.30
     ज़
    0.30
    Activations Density 0.003%

    No Known Activations