© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203100
    Prev
    Next
    INDEX
    Explanations

    iPhone X lidar

    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_12_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
    nial
    0.49
    لنا
    0.43
    rugated
    0.43
    URDAY
    0.42
     devotes
    0.41
    ொ
    0.40
    ㎖
    0.40
    itens
    0.40
    ハリ
    0.39
    ringar
    0.39
    POSITIVE LOGITS
    ("__
    0.44
    лата
    0.44
    vet
    0.43
    ົ້າ
    0.41
     मुठभे
    0.41
    諦
    0.39
     आत्म
    0.39
    pace
    0.38
    íos
    0.38
     જા
    0.37
    Activations Density 0.000%

    No Known Activations