© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203134
    Prev
    Next
    INDEX
    Explanations

    ://

    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
    휘
    0.39
    Headline
    0.36
     இன்ற
    0.35
    فرنس
    0.35
    하던
    0.35
    Golden
    0.34
    iphon
    0.34
    そうな
    0.34
    ContextProvider
    0.34
     run
    0.33
    POSITIVE LOGITS
     MAH
    0.42
     JEN
    0.42
     పి
    0.41
     pj
    0.41
     Ludwig
    0.40
    𝙝
    0.40
     भगत
    0.40
     p
    0.39
    尼
    0.39
    sbParams
    0.39
    Activations Density 0.000%

    No Known Activations