© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179942
    Prev
    Next
    INDEX
    Explanations

    credits clients Senior Software

    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_24_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
     фаразы
    0.48
    uals
    0.48
    ㎿
    0.45
     biến
    0.45
     ሃ
    0.45
     δια
    0.45
    ἦ
    0.45
    幣
    0.44
     られ
    0.42
    ệng
    0.42
    POSITIVE LOGITS
     \&
    0.43
    ми
    0.40
    द्ध
    0.39
    फु
    0.38
    高
    0.38
    మే
    0.38
    overlapping
    0.38
     aproximadamente
    0.37
    ---
    0.37
    and
    0.37
    Activations Density 0.000%

    No Known Activations