© 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. 109184
    Prev
    Next
    INDEX
    Explanations

    numerics libraries

    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
    ts
    1.55
    A
    1.50
    to
    1.31
    ties
    1.21
    ty
    1.20
    ta
    1.19
    h
    1.16
    de
    1.14
    Func
    1.14
    t
    1.13
    POSITIVE LOGITS
    ك
    1.36
    ين
    1.34
    ння
    1.31
     avaient
    1.29
    ی
    1.27
    б
    1.26
    ни
    1.22
    ці
    1.20
     alimentaires
    1.20
     on
    1.19
    Activations Density 0.000%

    No Known Activations