© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58408
    Prev
    Next
    INDEX
    Explanations

    comprehending

    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_2_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
    d
    2.16
    l
    2.02
    ל
    1.80
    t
    1.66
    ת
    1.63
    т
    1.61
    ה
    1.56
    s
    1.49
    ي
    1.47
    p
    1.41
    POSITIVE LOGITS
    )
    1.09
    ier
    0.97
    )]
    0.95
    )،
    0.92
    izes
    0.91
    ،
    0.88
     स्तर
    0.87
    )’
    0.87
    ät
    0.86
    ,’
    0.85
    Activations Density 0.000%

    No Known Activations