© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26662
    Prev
    Next
    INDEX
    Explanations

    capability and capacity

    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
    ுகிறார்கள்
    0.86
    し
    0.84
    padă
    0.81
    IN
    0.79
    ত
    0.79
    biggr
    0.78
    ுகிற
    0.77
    ט
    0.77
     Algunas
    0.75
    ക്കും
    0.72
    POSITIVE LOGITS
     capacity
    1.09
     Capacity
    1.02
     CAPACITY
    0.93
     de
    0.89
     kapas
    0.88
     kapac
    0.86
    Capacity
    0.86
    capacity
    0.85
     capacities
    0.84
    .
    0.82
    Activations Density 0.045%

    No Known Activations