© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205062
    Prev
    Next
    INDEX
    Explanations

    flower crown adornment

    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_6_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
    ant
    1.30
    q
    1.28
    ad
    1.27
    s
    1.24
     and
    1.23
    t
    1.23
     at
    1.18
    ’
    1.17
    ys
    1.13
    é
    1.10
    POSITIVE LOGITS
    1.11
    ною
    1.07
    fontein
    1.04
    fonso
    1.02
    TEN
    0.98
     Quân
    0.96
     Фурга
    0.95
    giờ
    0.95
    nemen
    0.95
    blätter
    0.95
    Activations Density 0.000%

    No Known Activations