© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91063
    Prev
    Next
    INDEX
    Explanations

    lockout policies, sulforaphane

    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
    oire
    0.63
    ⁵
    0.61
     leiden
    0.54
     digitized
    0.52
     beho
    0.52
     cuantit
    0.52
    atoren
    0.52
    정과
    0.51
     pés
    0.51
     виде
    0.50
    POSITIVE LOGITS
    та
    0.74
    )،
    0.72
    ங்கிணை
    0.70
    _
    0.70
    ),
    0.68
    یر
    0.67
     เป็น
    0.66
    리
    0.66
     }}
    0.65
     को
    0.63
    Activations Density 0.000%

    No Known Activations