© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31905
    Prev
    Next
    INDEX
    Explanations

    "is no" or "is a/an"

    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_7_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
    us
    0.69
    .
    0.66
    ৫
    0.66
    on
    0.66
    .​
    0.64
    .¹
    0.64
    cliente
    0.62
    np
    0.61
    z
    0.61
    onso
    0.60
    POSITIVE LOGITS
     rehearsals
    0.75
     at
    0.72
     into
    0.72
    কে
    0.71
     to
    0.67
     and
    0.65
     exhort
    0.65
    는
    0.63
    ਮ
    0.62
     invitations
    0.61
    Activations Density 0.003%

    No Known Activations