© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242953
    Prev
    Next
    INDEX
    Explanations

    spring release

    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_40_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
    JAVA
    0.46
     java
    0.46
    Java
    0.45
     JVM
    0.45
    maven
    0.43
     Jena
    0.42
    摺
    0.42
     Java
    0.41
    Sew
    0.41
    Actress
    0.40
    POSITIVE LOGITS
    oxys
    0.40
    teilt
    0.39
     Bu
    0.38
     ox
    0.37
    ariest
    0.37
    oxi
    0.36
    Bu
    0.36
    禦
    0.36
     PW
    0.35
    ixeira
    0.35
    Activations Density 0.000%

    No Known Activations