© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229296
    Prev
    Next
    INDEX
    Explanations

    안녕 and ity suffix 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_6_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
    ט
    1.09
    트
    1.05
    ت
    1.01
    т
    0.93
    스가
    0.88
    the
    0.87
    ות
    0.86
     boli
    0.84
    스를
    0.84
    טה
    0.84
    POSITIVE LOGITS
    f
    0.98
    Y
    0.93
    h
    0.91
     and
    0.85
    ail
    0.83
     I
    0.82
    father
    0.82
    hā
    0.80
    ral
    0.78
    Pseud
    0.78
    Activations Density 0.000%

    No Known Activations