© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115855
    Prev
    Next
    INDEX
    Explanations

    checks for emptiness or non-existence

    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_27_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
    தீ
    0.26
     propulsion
    0.26
    क्शन
    0.25
     malleable
    0.24
    Microelectronics
    0.24
     surplus
    0.24
     Dressing
    0.24
    틸
    0.24
     wundersch
    0.24
    ्लादेश
    0.24
    POSITIVE LOGITS
     पॅ
    0.27
     coordenada
    0.26
     emprego
    0.25
     gur
    0.25
    Combine
    0.25
     exactamente
    0.25
     avem
    0.24
     combinado
    0.24
     акчага
    0.24
    龕
    0.24
    Activations Density 0.002%

    No Known Activations