© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78430
    Prev
    Next
    INDEX
    Explanations

    existence and nonexistence

    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_29_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
     remand
    0.39
    떤
    0.38
    ffin
    0.37
    Alongside
    0.37
    Acetyl
    0.37
    Retry
    0.36
    Glo
    0.36
    CCI
    0.36
    敷
    0.35
    sächlich
    0.35
    POSITIVE LOGITS
     inexist
    0.52
    不存在
    0.49
     bisher
    0.46
     donde
    0.45
     OTHERWISE
    0.44
     tada
    0.43
     existência
    0.43
     where
    0.42
     bislang
    0.42
     nonexistent
    0.42
    Activations Density 0.043%

    No Known Activations