© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 203422
    Prev
    Next
    INDEX
    Explanations

    AWS ARNs and account IDs

    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_37_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
     faces
    0.37
    Researcher
    0.35
    曺
    0.35
     comunicazione
    0.35
     আফ্রিকার
    0.35
    Dr
    0.35
     произ
    0.34
    認証
    0.34
     континен
    0.34
     лица
    0.34
    POSITIVE LOGITS
    ":{"
    0.38
    ച്ചി
    0.38
    ッテリー
    0.37
    ﺴ
    0.37
     অবস্থান
    0.37
     visualize
    0.37
    toNumber
    0.36
     party
    0.36
     ally
    0.35
    वड
    0.35
    Activations Density 0.001%

    No Known Activations