© 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. 112336
    Prev
    Next
    INDEX
    Explanations

    malls

    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
    (
    1.80
    .
    1.73
    3
    1.22
    the
    1.21
    ;
    1.16
    (.*
    1.11
    j
    1.05
    건
    1.02
    ۔
    0.97
    The
    0.96
    POSITIVE LOGITS
     be
    1.70
     don
    1.25
    مي
    1.20
     dona
    1.13
     been
    1.05
     it
    1.04
    দূ
    1.02
     desarrolla
    1.01
     l
    0.98
    有一些
    0.98
    Activations Density 0.000%

    No Known Activations