© 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. 115503
    Prev
    Next
    INDEX
    Explanations

    investigation and legal proceedings

    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
    न्वयन
    0.46
     drunken
    0.41
     flam
    0.41
     σύμφωνα
    0.40
     पटाखे
    0.40
     stamped
    0.38
     mastic
    0.38
    骷
    0.38
     skinny
    0.38
     dement
    0.37
    POSITIVE LOGITS
     તપાસ
    0.46
     দুদকের
    0.45
     پذیر
    0.44
     তদন্ত
    0.43
     जांच
    0.42
     accepting
    0.42
     investigation
    0.40
    Accept
    0.40
     investigating
    0.40
    Prosecutors
    0.40
    Activations Density 0.014%

    No Known Activations