© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89654
    Prev
    Next
    INDEX
    Explanations

    position type summary reports changes

    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_3_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
     Position
    1.09
    Position
    1.07
     POSITION
    1.07
     position
    1.04
    <0x0D>
    0.99
     posicion
    0.93
     posición
    0.86
    position
    0.81
     posisi
    0.81
     posição
    0.80
    POSITIVE LOGITS
    a
    0.98
    ent
    0.86
    ه
    0.86
    hive
    0.82
    e
    0.79
    mild
    0.73
    o
    0.72
    ა
    0.72
    db
    0.71
    ة
    0.71
    Activations Density 0.001%

    No Known Activations