© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86267
    Prev
    Next
    INDEX
    Explanations

    axios import statements

    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_23_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
    Analysis
    0.51
    Explain
    0.47
    Check
    0.46
    Type
    0.44
    LinkedIn
    0.42
     CHECK
    0.42
    Substitution
    0.42
    ﺶ
    0.42
    Parser
    0.41
    Explore
    0.41
    POSITIVE LOGITS
     Were
    0.50
     Nara
    0.46
     insbesondere
    0.45
     Sanchez
    0.42
     Promised
    0.42
     exhibiting
    0.42
     Oda
    0.42
     Other
    0.41
     representando
    0.41
     perros
    0.40
    Activations Density 0.000%

    No Known Activations