© 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
    2. Gemma-3-27B-IT
    3. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 79061
    Prev
    Next
    INDEX
    Explanations

    logos, Repr, emplace, Topic

    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
    '
    2.38
    an
    2.19
    on
    1.95
     be
    1.86
    ר
    1.76
    of
    1.73
    י
    1.70
    по
    1.67
    c
    1.62
    (
    1.59
    POSITIVE LOGITS
    </h3>
    1.92
    </h5>
    1.53
    </h6>
    1.48
    ة
    1.44
    </h1>
    1.35
    <0x0D>
    1.28
    </s>
    1.23
    </h4>
    1.20
    </sup>
    1.18
     olika
    1.17
    Activations Density 0.000%

    No Known Activations