© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92431
    Prev
    Next
    INDEX
    Explanations

    words ending in ical

    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_11_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
    t
    0.57
     poch
    0.49
     eh
    0.47
     вполне
    0.47
     الكويت
    0.46
     poner
    0.46
     Anda
    0.45
     campe
    0.45
     Sk
    0.45
     воен
    0.45
    POSITIVE LOGITS
    ront
    0.64
    י
    0.62
    ح
    0.61
    isolated
    0.55
    Κα
    0.54
    atiable
    0.54
    ultra
    0.54
    σ
    0.54
    voltage
    0.54
    İZ
    0.53
    Activations Density 0.000%

    No Known Activations