© 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. 35726
    Prev
    Next
    INDEX
    Explanations

    spices and road bikes

    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
    rt
    0.73
    your
    0.72
    n
    0.71
    5
    0.69
    y
    0.68
    ’’’’
    0.68
    ların
    0.67
    nac
    0.67
    т
    0.66
    ry
    0.66
    POSITIVE LOGITS
     vento
    0.64
     tämän
    0.61
     ministra
    0.59
     বেশিরভাগ
    0.58
    的時間
    0.56
     لما
    0.55
     zoveel
    0.55
     Zeitpunkt
    0.55
     navegación
    0.55
     enthalten
    0.54
    Activations Density 0.004%

    No Known Activations