© 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. 202352
    Prev
    Next
    INDEX
    Explanations

    An rat

    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
     S
    0.52
     எஸ்
    0.45
     الس
    0.43
    ッケ
    0.40
     এস
    0.38
     Jest
    0.38
     എസ്
    0.37
     Ledger
    0.36
     พบ
    0.35
     uniform
    0.34
    POSITIVE LOGITS
    An
    0.47
     An
    0.44
    rat
    0.44
    Rat
    0.44
    밀
    0.44
     १
    0.43
     rat
    0.40
    Zd
    0.40
    Z
    0.40
    zmq
    0.39
    Activations Density 0.008%

    No Known Activations