© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45830
    Prev
    Next
    INDEX
    Explanations

    displaying borders or auto sizing

    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_22_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
     lorry
    0.45
     supremo
    0.39
    itan
    0.39
     cro
    0.39
    Კ
    0.38
    riek
    0.38
     lor
    0.38
     législ
    0.38
     rencana
    0.37
     Victoria
    0.37
    POSITIVE LOGITS
    )},
    0.43
     kills
    0.42
     슬
    0.40
    feels
    0.40
    。",
    0.38
    fordert
    0.38
     പഴയ
    0.38
    namespaces
    0.37
     paintball
    0.37
    translational
    0.37
    Activations Density 0.000%

    No Known Activations