© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83598
    Prev
    Next
    INDEX
    Explanations

    creamy texture, filling, or color

    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_0_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
    е
    1.55
    к
    1.41
    는
    1.41
                  
    1.18
    1.18
    ס
    1.16
    లో
    1.16
    是
    1.13
    а
    1.10
    中
    1.09
    POSITIVE LOGITS
    t
    2.30
    d
    1.52
    tive
    1.45
    i
    1.44
    n
    1.38
    se
    1.35
    ul
    1.30
    tól
    1.26
    daki
    1.25
    ták
    1.25
    Activations Density 0.001%

    No Known Activations