© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80294
    Prev
    Next
    INDEX
    Explanations

    specific cultures or regions

    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_53_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
     prototyp
    0.40
     pon
    0.39
    Pon
    0.39
     pote
    0.38
    ziger
    0.38
    PON
    0.37
    ssdk
    0.36
    𝐡
    0.36
    pointers
    0.36
    त्मा
    0.36
    POSITIVE LOGITS
     pelvic
    0.45
    пени
    0.45
     Pel
    0.43
    Pel
    0.43
     jawa
    0.41
     pel
    0.41
     voli
    0.41
     anului
    0.40
     Vol
    0.40
    জাহ
    0.39
    Activations Density 0.000%

    No Known Activations