© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163947
    Prev
    Next
    INDEX
    Explanations

    technical support and help

    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_31_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
     fichero
    0.39
     screened
    0.37
    veloped
    0.36
     plej
    0.36
     parol
    0.36
     penetrated
    0.35
    휼
    0.35
     struggle
    0.35
     покри
    0.35
    zungen
    0.34
    POSITIVE LOGITS
    Fem
    0.40
    ುತ್ತಿದೆ
    0.39
     Fem
    0.36
    Caucasian
    0.36
     |-
    0.36
     encode
    0.35
    butter
    0.35
     JAVA
    0.35
    🧔
    0.35
     javac
    0.34
    Activations Density 0.002%

    No Known Activations