© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122211
    Prev
    Next
    INDEX
    Explanations

    constantly putting

    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_37_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
     мәкалә
    0.25
    izontally
    0.24
     excavated
    0.24
     vassal
    0.23
    γον
    0.23
     تضيفلها
    0.23
     仕様
    0.22
     _$_
    0.22
     पीठ
    0.22
     Unable
    0.22
    POSITIVE LOGITS
    loadConst
    0.29
    ők
    0.27
    洛
    0.25
     CS
    0.25
    Académie
    0.24
    …"
    0.24
    urés
    0.24
     чер
    0.23
     renderEncoder
    0.23
    शेदपुर
    0.23
    Activations Density 0.322%

    No Known Activations