© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145684
    Prev
    Next
    INDEX
    Explanations

    favorable outcomes

    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_59_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
     दाह
    0.41
     الفر
    0.35
    oxia
    0.34
    培养
    0.34
    merzen
    0.33
    衮
    0.33
    ridges
    0.33
     Aro
    0.32
     copos
    0.32
     అ
    0.32
    POSITIVE LOGITS
     favorable
    2.48
     favourable
    2.34
     unfavorable
    2.08
     unfavourable
    2.05
     favorably
    1.97
     favorables
    1.92
     благоприят
    1.84
     favourably
    1.83
     favore
    1.59
     F
    1.56
    Activations Density 0.011%

    No Known Activations