© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108823
    Prev
    Next
    INDEX
    Explanations

    Uq-

    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_1_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
    )
    0.95
    ლებ
    0.92
    sembl
    0.91
    ]
    0.90
    ફેદ
    0.89
    سم
    0.88
     isotherms
    0.88
    nels
    0.87
    мер
    0.86
    sembled
    0.86
    POSITIVE LOGITS
    h
    1.43
    在
    1.26
    માં
    1.20
    '
    1.18
    in
    1.17
     in
    1.16
    f
    1.15
    кових
    1.12
    도
    1.12
    타
    1.11
    Activations Density 0.000%

    No Known Activations