© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45843
    Prev
    Next
    INDEX
    Explanations

    allows, makes, means, can

    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
    ouncy
    0.38
     Verb
    0.36
     navn
    0.36
    otic
    0.35
     gsap
    0.35
    aconit
    0.35
    otive
    0.35
    »:
    0.35
    最重要的
    0.35
    zahl
    0.34
    POSITIVE LOGITS
    ilege
    0.36
     ठाकुर
    0.36
     segnal
    0.35
    ចំ
    0.35
    경상
    0.34
     Enfer
    0.34
     정보
    0.34
     Kranken
    0.34
     जना
    0.34
    стки
    0.33
    Activations Density 0.023%

    No Known Activations