© 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. 134344
    Prev
    Next
    INDEX
    Explanations

    stick figure

    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
     δο
    0.94
     ד
    0.94
    breeding
    0.89
     calving
    0.87
     барои
    0.85
    ađ
    0.83
    𝟰
    0.82
     سالب
    0.78
     מ
    0.78
     क़
    0.77
    POSITIVE LOGITS
    ة
    1.29
    ί
    1.26
    ing
    1.20
    í
    1.09
    at
    1.02
    си
    1.00
    is
    0.99
    ",
    0.97
    u
    0.96
    A
    0.95
    Activations Density 0.000%

    No Known Activations