© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130110
    Prev
    Next
    INDEX
    Explanations

    supplied by

    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
    。
    1.21
    )。
    1.15
    اک
    0.98
    。「
    0.97
    ಬ್ಬಿಣ
    0.97
    )、
    0.96
    τή
    0.91
    不仅
    0.90
    이다
    0.89
    has
    0.89
    POSITIVE LOGITS
    an
    1.40
    ہ
    1.22
    g
    1.20
     or
    1.16
    ان
    1.16
    ка
    1.13
    ı
    1.09
    í
    1.09
    ă
    1.06
    ة
    1.05
    Activations Density 0.000%

    No Known Activations