© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24625
    Prev
    Next
    INDEX
    Explanations

    acronyms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     aż
    0.42
    ж
    0.41
     až
    0.40
    ž
    0.39
     BOP
    0.39
     dl
    0.38
    dl
    0.38
    BO
    0.37
    тить
    0.37
    حدى
    0.37
    POSITIVE LOGITS
    N
    0.52
     N
    0.44
    MC
    0.41
    MLE
    0.41
     trusts
    0.38
    ச்சர்
    0.38
    uft
    0.37
     MC
    0.35
    vi
    0.35
    edt
    0.35
    Activations Density 0.014%

    No Known Activations