© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106984
    Prev
    Next
    INDEX
    Explanations

    positive and negative changes

    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_1_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
    c
    1.61
    ين
    1.45
    t
    1.41
    p
    1.33
    k
    1.33
    ก
    1.27
    ਾ
    1.24
     was
    1.19
    nx
    1.16
    czna
    1.08
    POSITIVE LOGITS
    I
    1.21
    ),
    1.13
    ;
    1.12
    )،
    1.03
    Don
    0.98
    ?
    0.97
    মেন্ট
    0.92
     banget
    0.90
    )}
    0.90
    Highway
    0.89
    Activations Density 0.001%

    No Known Activations