© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151150
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    {\
    0.48
    a
    0.45
    if
    0.45
    and
    0.45
    và
    0.44
    ain
    0.44
     >
    0.43
    Ꭹ
    0.43
    𝐚
    0.41
    illation
    0.40
    POSITIVE LOGITS
     inactive
    0.66
     unfounded
    0.64
     stagnant
    0.63
     empty
    0.60
     unstable
    0.59
     obsolete
    0.59
     inanimate
    0.59
     unclean
    0.58
     immobile
    0.57
     inconclusive
    0.57
    Activations Density 0.010%

    No Known Activations