© 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. 161635
    Prev
    Next
    INDEX
    Explanations

    crumbles and fumbles

    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
    c
    1.58
    i
    1.52
    l
    1.42
    b
    1.41
    k
    1.34
    in
    1.30
    u
    1.27
    <0x91>
    1.14
    lere
    1.13
    ية
    1.13
    POSITIVE LOGITS
     you
    1.63
     when
    1.09
     can
    1.04
     the
    1.02
     will
    1.02
    ке
    0.99
    0
    0.99
    ਰ
    0.99
     trusty
    0.98
     than
    0.98
    Activations Density 0.000%

    No Known Activations