© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37792
    Prev
    Next
    INDEX
    Explanations

    names

    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_57_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
     annih
    0.43
     Walling
    0.41
    曛
    0.41
     nyaman
    0.40
     क्वेश्च
    0.40
     होईल
    0.40
     Nikol
    0.39
    ⓶
    0.39
     जाईल
    0.39
    ニング
    0.38
    POSITIVE LOGITS
    ú
    0.45
    chat
    0.45
    á
    0.41
    amos
    0.40
    Á
    0.40
    Chat
    0.40
    áfico
    0.39
     no
    0.38
    ás
    0.38
    éc
    0.38
    Activations Density 0.000%

    No Known Activations