© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90844
    Prev
    Next
    INDEX
    Explanations

    horror stories

    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
    getImageFolder
    0.37
     ر
    0.36
     가장
    0.35
     الر
    0.35
     火
    0.35
     р
    0.35
    ្អ
    0.34
     vivido
    0.34
     ဒ
    0.34
     эту
    0.33
    POSITIVE LOGITS
    from
    0.42
    From
    0.32
    at
    0.31
    #
    0.31
    players
    0.30
    ურთი
    0.30
    peb
    0.30
    umption
    0.29
    Off
    0.29
    them
    0.28
    Activations Density 0.021%

    No Known Activations