© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82220
    Prev
    Next
    INDEX
    Explanations

    swamp and extinguish

    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_0_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
    지
    2.16
    s
    1.93
    ა
    1.84
    자
    1.75
    z
    1.70
    지에
    1.63
    m
    1.63
    have
    1.61
    ur
    1.59
    मधील
    1.59
    POSITIVE LOGITS
     is
    1.82
     was
    1.54
    1.48
     в
    1.38
     an
    1.20
     في
    1.20
    };
    1.16
    `}
    1.16
     అనేది
    1.15
    <0x9D>
    1.13
    Activations Density 0.000%

    No Known Activations