© 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. 161180
    Prev
    Next
    INDEX
    Explanations

    dims, cliques, affiliation

    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
    ро
    1.48
    ре
    1.41
    quela
    1.41
     luisant
    1.26
    $)$.
    1.26
    ला
    1.25
    ков
    1.20
    いた
    1.20
    س
    1.13
    ier
    1.11
    POSITIVE LOGITS
    ר
    1.56
    ни
    1.45
    ే
    1.41
     L
    1.28
    -
    1.24
     The
    1.23
    is
    1.20
    y
    1.20
     A
    1.15
    n
    1.15
    Activations Density 0.000%

    No Known Activations