© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139469
    Prev
    Next
    INDEX
    Explanations

    sports betting and tipsters

    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_12_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
    掸
    0.56
    撣
    0.55
     Kom
    0.52
    nya
    0.51
    Kom
    0.51
    AN
    0.49
    தான
    0.49
    K
    0.49
    KOM
    0.49
    کان
    0.46
    POSITIVE LOGITS
     chiffre
    0.57
     亠
    0.56
     avenir
    0.55
     politique
    0.52
    ajib
    0.51
    чиго
    0.50
     codons
    0.49
     analyse
    0.49
     calendrier
    0.49
     фаразлары
    0.48
    Activations Density 0.000%

    No Known Activations