© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39469
    Prev
    Next
    INDEX
    Explanations

    grace period

    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_11_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
    ÇÃO
    0.59
    皐
    0.56
    𝑳
    0.56
    ிக
    0.55
    자
    0.55
     sejumlah
    0.53
    𝙇
    0.53
    兟
    0.52
    ệnh
    0.52
     sabbam
    0.52
    POSITIVE LOGITS
    payment
    0.63
    powder
    0.60
    grace
    0.55
    engined
    0.55
    holy
    0.55
    dodge
    0.54
    toy
    0.53
    plaintext
    0.53
    pay
    0.52
    wood
    0.51
    Activations Density 0.014%

    No Known Activations