© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99111
    Prev
    Next
    INDEX
    Explanations

    limiting and throttling

    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_16_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
    ation
    0.13
     Derived
    0.13
    ed
    0.13
     производится
    0.13
     natomiast
    0.12
    n
    0.12
     Eliminate
    0.12
     Verwendung
    0.12
     pribli
    0.12
     producido
    0.12
    POSITIVE LOGITS
    렜
    0.16
     communicative
    0.16
     anx
    0.14
     headerShown
    0.13
    Database
    0.13
     trachea
    0.13
    きた
    0.13
    TableHeader
    0.13
     patient
    0.13
     channel
    0.13
    Activations Density 0.015%

    No Known Activations