© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60389
    Prev
    Next
    INDEX
    Explanations

    comparing the two

    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
    m
    1.33
    t
    1.09
    an
    1.09
    on
    1.08
    _
    1.03
    N
    1.02
    浯
    1.00
     estratégico
    0.96
    وم
    0.96
     THAT
    0.95
    POSITIVE LOGITS
    in
    1.65
    ir
    1.48
    ی
    1.38
    (
    1.30
    هم
    1.29
    u
    1.22
    ва
    1.18
     pyrolysis
    1.16
    ના
    1.10
    aneous
    1.10
    Activations Density 0.003%

    No Known Activations