© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183115
    Prev
    Next
    INDEX
    Explanations

    maximum, minimum, largest, smallest

    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_29_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
     Naturally
    0.39
     अखंड
    0.38
     bottoms
    0.37
    brooke
    0.36
    duh
    0.36
    ⎝
    0.35
     warmest
    0.35
     Like
    0.35
    ള്ള
    0.35
     So
    0.35
    POSITIVE LOGITS
     mixte
    0.41
     değil
    0.41
    ໍາ
    0.38
     raczej
    0.37
     प्रवृत्ति
    0.37
    汽
    0.37
     plutôt
    0.36
    リオ
    0.36
    ocide
    0.36
    ਯ
    0.36
    Activations Density 0.001%

    No Known Activations