© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49699
    Prev
    Next
    INDEX
    Explanations

    которые

    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_55_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
     –
    0.93
     —
    0.90
     -
    0.88
     −
    0.76
     --
    0.70
     －
    0.70
     ―
    0.67
     $-$
    0.65
     ـ
    0.63
    —
    0.60
    POSITIVE LOGITS
     seems
    0.45
     might
    0.45
     seemed
    0.44
     seem
    0.44
     maint
    0.43
     pulls
    0.41
     enqu
    0.41
    潜在
    0.40
     acknowledges
    0.39
    amah
    0.39
    Activations Density 0.002%

    No Known Activations