© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39276
    Prev
    Next
    INDEX
    Explanations

    te

    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_57_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
     le
    0.42
    aine
    0.36
     neces
    0.36
    が必要
    0.35
     Le
    0.35
    ्रु
    0.34
     राइट
    0.34
     ត
    0.33
     Jeter
    0.33
    lat
    0.33
    POSITIVE LOGITS
    стях
    0.43
     quét
    0.41
    вої
    0.40
     йөк
    0.40
     setTo
    0.38
     வருகின்றன
    0.38
     பத
    0.37
     smi
    0.37
    ೭
    0.37
     edilmesi
    0.36
    Activations Density 0.004%

    No Known Activations