© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217291
    Prev
    Next
    INDEX
    Explanations

    at [organization/group]

    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
    abras
    0.36
    pland
    0.35
    酆
    0.35
    WT
    0.35
    eers
    0.34
    MPs
    0.33
    μως
    0.33
     зараз
    0.33
    uments
    0.32
    MZ
    0.32
    POSITIVE LOGITS
    楽
    0.43
    ᡠ
    0.38
     Mississippi
    0.38
     Northwest
    0.38
     Prä
    0.36
     видите
    0.36
    Meine
    0.35
     Meine
    0.35
     Colonial
    0.35
     इस्लामिक
    0.35
    Activations Density 0.001%

    No Known Activations