© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260084
    Prev
    Next
    INDEX
    Explanations

    distribution, class, trait, code, random

    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_22_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
     میان
    0.50
     cỏ
    0.48
     orçamento
    0.45
     plagiarism
    0.43
     Alfa
    0.43
     latest
    0.42
    最新
    0.42
    斛
    0.42
    acies
    0.41
     artefacts
    0.41
    POSITIVE LOGITS
    erçe
    0.42
    %
    0.41
    teni
    0.38
    %=
    0.38
     பெய
    0.38
    ller
    0.38
    ASP
    0.38
    %-
    0.37
    、、
    0.37
     تعريف
    0.37
    Activations Density 0.000%

    No Known Activations