© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213794
    Prev
    Next
    INDEX
    Explanations

    Japanese greetings

    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_50_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
    ᠢ
    0.48
    闥
    0.46
     VE
    0.45
    IFICATE
    0.42
     रि
    0.41
    OTE
    0.41
    ̍
    0.39
     वेक्टर
    0.39
    製作
    0.38
     vektor
    0.38
    POSITIVE LOGITS
    腰
    0.49
    わ
    0.49
     wa
    0.44
     waist
    0.41
    ワ
    0.41
    wa
    0.41
     わ
    0.41
    Sharma
    0.41
    WA
    0.40
    Wa
    0.40
    Activations Density 0.000%

    No Known Activations