© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51340
    Prev
    Next
    INDEX
    Explanations

    face and body products

    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
     запро
    0.42
    wild
    0.41
     सस्ती
    0.41
     birthdays
    0.39
     Affidavit
    0.39
    Nomin
    0.39
    ﺰ
    0.38
    口座
    0.37
    privileged
    0.37
     collateral
    0.37
    POSITIVE LOGITS
     pitch
    0.53
     Pitch
    0.45
    pitch
    0.44
    Pitch
    0.44
     pitches
    0.44
     Brewing
    0.41
     TECHNI
    0.40
     polycarbonate
    0.39
     polymerized
    0.38
     ale
    0.37
    Activations Density 0.002%

    No Known Activations