© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90197
    Prev
    Next
    INDEX
    Explanations

    Bitbucket

    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_3_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
    б
    0.82
    в
    0.74
    𝚐
    0.68
    govern
    0.68
    ף
    0.68
    gin
    0.66
     prur
    0.66
    ス
    0.66
     pressur
    0.65
    𝗴
    0.65
    POSITIVE LOGITS
    um
    0.82
    。「
    0.74
    ő
    0.68
    ienda
    0.68
    '};
    0.68
    al
    0.65
    。“
    0.65
    。
    0.65
    il
    0.64
    alang
    0.64
    Activations Density 0.001%

    No Known Activations