© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138115
    Prev
    Next
    INDEX
    Explanations

    charismatic wrestler or cuddly companion

    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
    ėjo
    0.64
    čk
    0.63
    SendData
    0.60
    铷
    0.60
    સમ
    0.59
    O
    0.59
    数据
    0.59
     ਸਿੰ
    0.59
     کردند
    0.58
    Cris
    0.58
    POSITIVE LOGITS
    al
    0.65
     gimnas
    0.63
    ;
    0.59
     kilka
    0.59
     tyrant
    0.59
     mañana
    0.58
     dislike
    0.57
     dangerously
    0.57
    a
    0.55
     principales
    0.55
    Activations Density 0.000%

    No Known Activations