© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141062
    Prev
    Next
    INDEX
    Explanations

    identifying, fixing

    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_46_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
     procesu
    0.40
     Proses
    0.38
     సె
    0.37
     |-
    0.37
    proses
    0.37
    ⟢
    0.37
    奇
    0.37
    鈳
    0.36
     proses
    0.36
     Prozess
    0.36
    POSITIVE LOGITS
     valves
    0.45
     fixing
    0.44
     Valves
    0.44
     iza
    0.43
     identifying
    0.41
    telefon
    0.41
     spotting
    0.41
     consulting
    0.40
    ீ
    0.40
     hiding
    0.39
    Activations Density 0.002%

    No Known Activations