© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201746
    Prev
    Next
    INDEX
    Explanations

    про

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    Պ
    0.46
     Krieg
    0.43
    ્રી
    0.43
     அடித்த
    0.42
    руются
    0.41
    ណ្ឌ
    0.40
    聽
    0.39
    ի
    0.39
     Indian
    0.39
     số
    0.38
    POSITIVE LOGITS
     бла
    0.38
    cloudinary
    0.36
     фра
    0.34
    toByteArray
    0.34
     |_
    0.33
    )$\
    0.33
    blah
    0.33
     messagebox
    0.32
    linebreak
    0.32
    zoa
    0.32
    Activations Density 0.001%

    No Known Activations