© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232742
    Prev
    Next
    INDEX
    Explanations

    residual manufacturing chemicals

    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_6_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
    ’
    1.26
    ;
    1.01
     danni
    0.86
     потому
    0.84
     лише
    0.82
     passaggio
    0.82
     perished
    0.82
     corsa
    0.82
     σε
    0.81
     hairy
    0.81
    POSITIVE LOGITS
    is
    1.38
    ag
    1.35
    I
    1.23
    ال
    1.20
    ار
    1.16
    ing
    1.15
    on
    1.14
    ر
    1.13
    ق
    1.13
    ol
    1.09
    Activations Density 0.000%

    No Known Activations