© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52156
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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_30_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
     mesela
    0.46
    ؟!
    0.40
    ।)
    0.39
     例えば
    0.39
     لاحظوا
    0.37
    для
    0.37
    ؟
    0.37
    ੌਰ
    0.37
     wiem
    0.36
     只
    0.36
    POSITIVE LOGITS
     Abi
    0.43
    lli
    0.39
    Abi
    0.39
     பத
    0.37
     Lincoln
    0.37
    abella
    0.37
     attempting
    0.36
     poised
    0.36
     office
    0.36
     Dash
    0.36
    Activations Density 0.023%

    No Known Activations