© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168842
    Prev
    Next
    INDEX
    Explanations

    Be

    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_56_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
    là
    0.42
    彌
    0.39
    ដែលមាន
    0.37
     Th
    0.37
    াপন্ন
    0.36
    គឺជា
    0.36
     थरूर
    0.36
    assign
    0.35
    пита
    0.35
    ਥ
    0.35
    POSITIVE LOGITS
     fore
    0.58
    fore
    0.51
     Fore
    0.51
    Fore
    0.42
     concerned
    0.41
     fuera
    0.40
    តែ
    0.36
     strument
    0.36
    igno
    0.36
     they
    0.35
    Activations Density 0.000%

    No Known Activations