© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251998
    Prev
    Next
    INDEX
    Explanations

    map

    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
     “
    0.56
     '#
    0.46
    ”
    0.45
     ‘
    0.44
    ”…
    0.44
     “[
    0.43
     “(
    0.42
    ”)
    0.41
    :”
    0.41
    )”
    0.40
    POSITIVE LOGITS
     ("
    0.58
     („
    0.52
     ('
    0.42
     (\"
    0.41
     attributed
    0.40
    ™,
    0.40
     Attribution
    0.38
     Pos
    0.37
    ^{*},
    0.37
     அல்லது
    0.37
    Activations Density 0.000%

    No Known Activations