© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66618
    Prev
    Next
    INDEX
    Explanations

    sun

    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_46_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
     eyeliner
    0.42
     liner
    0.42
     curling
    0.40
    indrical
    0.38
     actomyosin
    0.38
    毕
    0.38
    一种
    0.37
     pact
    0.37
     furnace
    0.37
     etiquette
    0.37
    POSITIVE LOGITS
    hounds
    0.45
     (“
    0.39
    ClickHandler
    0.38
    qz
    0.35
    Pref
    0.35
    moon
    0.35
    ycle
    0.35
    モス
    0.35
    Ṭ
    0.35
    PC
    0.34
    Activations Density 0.002%

    No Known Activations