© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214711
    Prev
    Next
    INDEX
    Explanations

    thrifting or tarp

    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_5_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
    t
    2.34
    ل
    1.77
    l
    1.52
    л
    1.51
    r
    1.46
    ル
    1.45
    c
    1.22
    b
    1.21
    ur
    1.20
    tive
    1.19
    POSITIVE LOGITS
     in
    1.14
     hydrolyzed
    1.09
    ți
    1.03
     bailout
    0.92
     parametri
    0.87
     ljud
    0.86
    も含
    0.86
    ’
    0.86
    ólito
    0.84
     improb
    0.84
    Activations Density 0.000%

    No Known Activations