© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134310
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be'

    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_6_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
    لي
    0.77
    לות
    0.76
    ون
    0.75
    t
    0.68
    ל
    0.66
    される
    0.66
    ции
    0.64
    َاب
    0.64
    sj
    0.64
    ونها
    0.64
    POSITIVE LOGITS
    0
    0.90
    S
    0.88
    I
    0.86
    E
    0.80
    isation
    0.75
    O
    0.75
    ay
    0.71
    н
    0.71
    ade
    0.68
    ceived
    0.68
    Activations Density 0.010%

    No Known Activations