© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228379
    Prev
    Next
    INDEX
    Explanations

    i.e. or e.g

    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
     FIX
    0.45
    𝗗
    0.44
     FIC
    0.40
     FIXED
    0.40
    嗲
    0.39
     REC
    0.37
     Dör
    0.37
     ôn
    0.37
    ERT
    0.37
    缡
    0.36
    POSITIVE LOGITS
    loin
    0.42
    tak
    0.41
     tak
    0.38
     cess
    0.37
     sandals
    0.37
    difficulty
    0.37
    Consec
    0.36
    chein
    0.35
    ované
    0.35
    queur
    0.34
    Activations Density 0.000%

    No Known Activations