© 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
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 604
    Prev
    Next
    INDEX
    Explanations

    8-digit numbers

    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_38_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
    ilio
    0.35
     Fors
    0.35
    ཉ
    0.35
    ☞
    0.35
     لجنة
    0.34
    刺
    0.34
     фран
    0.34
    灬
    0.34
    ніза
    0.33
     Colonia
    0.33
    POSITIVE LOGITS
     Altman
    0.37
     attract
    0.36
    দা
    0.36
    uur
    0.36
     žal
    0.35
     pliable
    0.35
    uga
    0.34
    derive
    0.33
    meet
    0.33
     Broker
    0.33
    Activations Density 0.100%

    No Known Activations