© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149895
    Prev
    Next
    INDEX
    Explanations

    Prote

    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_60_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
    δ
    0.47
    at
    0.45
    ds
    0.43
    slice
    0.43
     prolonged
    0.41
    comple
    0.41
    desa
    0.41
    slate
    0.41
    delta
    0.40
    dfs
    0.40
    POSITIVE LOGITS
    ={(
    0.44
     kalan
    0.43
    uert
    0.42
     kiel
    0.41
     kt
    0.40
    ADIUM
    0.39
    IOUS
    0.37
    Klein
    0.37
    uously
    0.37
    ന്യൂ
    0.37
    Activations Density 0.000%

    No Known Activations