© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120461
    Prev
    Next
    INDEX
    Explanations

    words followed by comma

    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_27_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
    楦
    0.37
     hym
    0.37
     ಮತ್ತ
    0.37
    െടുത്ത
    0.35
     questioned
    0.35
    zyma
    0.35
    anwhile
    0.34
     интеллек
    0.34
     জিজ্ঞাস
    0.33
     Mentre
    0.33
    POSITIVE LOGITS
    ilov
    0.39
     torches
    0.39
     এটা
    0.38
    should
    0.38
    ග
    0.37
    тков
    0.36
    າດ
    0.36
    trib
    0.36
     ratchet
    0.35
    这是一
    0.35
    Activations Density 0.001%

    No Known Activations