© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157449
    Prev
    Next
    INDEX
    Explanations

    immeasurable

    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_2_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
    с
    1.54
    ہ
    1.31
    ль
    1.25
    ン
    1.24
    ח
    1.15
    ह
    1.11
    س
    1.10
    רו
    1.02
    б
    0.98
    े
    0.96
    POSITIVE LOGITS
    IS
    1.13
    ER
    1.05
    ↵
    1.02
    ELL
    0.98
     الشركات
    0.93
    ot
    0.92
    é
    0.89
    ERSON
    0.89
    ется
    0.88
    য়ের
    0.88
    Activations Density 0.000%

    No Known Activations