© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236099
    Prev
    Next
    INDEX
    Explanations

    indoor heating

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     getInput
    0.38
     अहमदाबाद
    0.38
     debating
    0.37
    amenti
    0.37
    폄
    0.37
     discomfort
    0.36
     упомина
    0.36
     textual
    0.35
    improvements
    0.35
     baking
    0.34
    POSITIVE LOGITS
    Log
    0.46
    hash
    0.46
    Hash
    0.42
    HASH
    0.42
     Hash
    0.41
     Knock
    0.40
     V
    0.39
     Cal
    0.39
     base
    0.39
    াকার
    0.38
    Activations Density 0.002%

    No Known Activations