© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81679
    Prev
    Next
    INDEX
    Explanations

    culprit or culvert

    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_0_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
    ৩
    1.52
    ோ
    1.49
    д
    1.48
    el
    1.46
    ৭
    1.44
    т
    1.41
     roto
    1.36
    ли
    1.34
    3
    1.34
    '
    1.33
    POSITIVE LOGITS
     нажа
    1.23
    সহ
    1.13
    P
    1.09
    D
    1.09
    C
    1.08
    br
    1.02
    থাৎ
    1.02
    ند
    1.00
     установ
    1.00
    čky
    0.99
    Activations Density 0.000%

    No Known Activations