© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194189
    Prev
    Next
    INDEX
    Explanations

    accessing articles and papers

    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_27_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
     __(
    0.44
     phân
    0.44
     зда
    0.43
     списка
    0.38
     messagebox
    0.38
    Ele
    0.37
     wèi
    0.37
     SPORT
    0.36
    tDBOutput
    0.36
     __
    0.35
    POSITIVE LOGITS
    pe
    0.46
    possible
    0.42
    arti
    0.42
    hement
    0.41
     queremos
    0.40
    qr
    0.40
    zees
    0.40
    pos
    0.39
    ynthesis
    0.39
     quiero
    0.38
    Activations Density 0.000%

    No Known Activations