© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43794
    Prev
    Next
    INDEX
    Explanations

    keywords, protocol registration

    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_13_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
    З
    0.47
    다
    0.46
    அ
    0.45
    อ
    0.44
     synonymous
    0.43
    일
    0.43
    জ
    0.42
    약
    0.42
     approx
    0.40
    avascript
    0.40
    POSITIVE LOGITS
     McGuire
    0.45
    MNumber
    0.44
     Pinto
    0.43
     Readiness
    0.43
    喽
    0.43
     iga
    0.43
     आईआई
    0.43
    küm
    0.42
    MENT
    0.42
     Huge
    0.42
    Activations Density 0.001%

    No Known Activations