© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43893
    Prev
    Next
    INDEX
    Explanations

    confidentiality, integrity, availability

    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_13_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
    socketState
    0.23
    ार्टम
    0.22
    ₨
    0.21
    angleright
    0.20
    foration
    0.20
     pptd
    0.20
     arthritis
    0.19
    ialog
    0.19
    measuredangle
    0.19
    household
    0.19
    POSITIVE LOGITS
    “[
    0.22
    “(
    0.21
     przede
    0.21
    “
    0.21
    でした
    0.20
     el
    0.20
    “-
    0.20
     толькі
    0.20
     kellett
    0.20
    不用
    0.19
    Activations Density 0.014%

    No Known Activations