© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100376
    Prev
    Next
    INDEX
    Explanations

    recovery runs

    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_14_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
    d
    0.64
     for
    0.63
     syll
    0.60
     add
    0.59
     or
    0.59
     amph
    0.59
     flux
    0.59
     under
    0.58
     fos
    0.57
     allele
    0.57
    POSITIVE LOGITS
     букмекерлик
    0.66
     Казіно
    0.56
    <unused264>
    0.56
     Elektrokh
    0.54
    blockchain
    0.54
     Counseling
    0.54
    ecake
    0.54
    хран
    0.54
    берриз
    0.54
     Paf
    0.53
    Activations Density 0.001%

    No Known Activations