© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51170
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese words

    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_30_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
    CHAR
    0.42
    newlines
    0.41
    احث
    0.40
    ELSE
    0.40
     नती
    0.40
    ónicos
    0.40
    洌
    0.39
     সাহায্যের
    0.39
    parametric
    0.39
     instância
    0.39
    POSITIVE LOGITS
     sensual
    0.48
     Strah
    0.45
     assessment
    0.45
    ด์
    0.44
     No
    0.44
    우스
    0.41
     Trevelyan
    0.41
     assess
    0.40
     occasionally
    0.40
    즈
    0.40
    Activations Density 0.003%

    No Known Activations