© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195760
    Prev
    Next
    INDEX
    Explanations

    following statements true or false

    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_26_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
    imcoords
    0.47
    áló
    0.43
    ultat
    0.42
    帛
    0.42
    yyati
    0.42
     uphol
    0.41
     équipé
    0.40
    FirebaseAuth
    0.40
    ரைய
    0.39
     Übersetzung
    0.39
    POSITIVE LOGITS
     D
    0.41
     अक्सर
    0.39
     polling
    0.39
    ear
    0.38
    alous
    0.38
    D
    0.38
    *
    0.37
    -
    0.37
     established
    0.36
     Field
    0.36
    Activations Density 0.000%

    No Known Activations