© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50191
    Prev
    Next
    INDEX
    Explanations

    future tense verb endings

    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_10_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
    j
    1.22
    w
    0.94
    v
    0.84
    ab
    0.81
    amar
    0.81
    u
    0.79
    im
    0.79
    ire
    0.77
    s
    0.77
    aw
    0.75
    POSITIVE LOGITS
     be
    0.75
     cardio
    0.75
    зора
    0.75
    grado
    0.74
     fermion
    0.74
     donut
    0.72
     ice
    0.71
     χρό
    0.71
     카
    0.71
     pares
    0.70
    Activations Density 0.001%

    No Known Activations