© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219295
    Prev
    Next
    INDEX
    Explanations

    assuming zero or non-zero

    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_31_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
     saada
    0.38
     (§
    0.38
     blackberries
    0.38
     worksheets
    0.38
     hojas
    0.38
     transparen
    0.37
     slaves
    0.37
     (*
    0.37
     («
    0.37
     demonstrations
    0.36
    POSITIVE LOGITS
    because
    0.40
     quedaría
    0.39
     посту
    0.38
    Huh
    0.37
     Implicit
    0.36
    仍在
    0.36
    yssey
    0.36
    implicitly
    0.36
    μένου
    0.35
    ämä
    0.35
    Activations Density 0.000%

    No Known Activations