© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132684
    Prev
    Next
    INDEX
    Explanations

    whale

    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_1_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
    し
    1.52
    τή
    1.34
    보는
    1.26
    ل
    1.19
    л
    1.16
     (
    1.16
    ться
    1.04
    ри
    1.02
    п
    1.02
    {(
    1.01
    POSITIVE LOGITS
    ent
    1.25
    d
    1.21
    هم
    1.19
    ال
    1.16
    in
    1.10
    it
    1.02
    ע
    1.02
    s
    1.00
    ه
    0.99
    dal
    0.96
    Activations Density 0.000%

    No Known Activations