© 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. 107591
    Prev
    Next
    INDEX
    Explanations

    Eliza and ELISA

    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
    <0x0D>
    1.62
    ного
    1.41
    ৫
    1.36
    1.34
    (
    1.29
    1.19
    </h3>
    1.18
    </h1>
    1.11
    ление
    1.10
    ться
    1.07
    POSITIVE LOGITS
    ح
    1.50
    the
    1.26
    ма
    1.23
    ك
    1.16
    2
    1.15
    over
    1.12
    기
    1.12
     as
    1.08
    на
    1.07
    ene
    1.07
    Activations Density 0.000%

    No Known Activations