© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100116
    Prev
    Next
    INDEX
    Explanations

    break down

    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_14_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
            
    0.67
    y
    0.64
    nu
    0.64
    if
    0.60
     When
    0.59
    FS
    0.59
    NIH
    0.58
    mic
    0.58
    INI
    0.58
    nois
    0.58
    POSITIVE LOGITS
    。<
    0.60
     guiclass
    0.59
     заболевания
    0.59
     блока
    0.59
     enfermedad
    0.57
     posición
    0.57
    ?<
    0.56
     положении
    0.55
     ενώ
    0.55
    ,<
    0.54
    Activations Density 0.000%

    No Known Activations