© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142604
    Prev
    Next
    INDEX
    Explanations

    dipped in liquid or substance

    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
     in
    1.64
    ท
    1.52
     I
    1.51
    ו
    1.50
    in
    1.49
     A
    1.48
    在
    1.47
    ння
    1.42
    </h3>
    1.38
    ?
    1.38
    POSITIVE LOGITS
    st
    1.80
    us
    1.49
    0
    1.30
    r
    1.27
    b
    1.26
    ای
    1.25
    ᱐
    1.23
    6
    1.21
    is
    1.20
    AND
    1.20
    Activations Density 0.000%

    No Known Activations