© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6620
    Prev
    Next
    INDEX
    Explanations

    author citations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    殮
    0.31
    ⚠
    0.30
     siedz
    0.30
     nachhalt
    0.29
    袭击
    0.29
     बुध
    0.29
     daarom
    0.29
    Insertion
    0.29
     reelection
    0.29
    ἧ
    0.29
    POSITIVE LOGITS
    éis
    0.29
     Eisen
    0.29
     SP
    0.29
     AP
    0.28
     Ridge
    0.27
     Collective
    0.27
    ности
    0.27
    agno
    0.27
     G
    0.26
     EVs
    0.26
    Activations Density 0.029%

    No Known Activations