© 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. 78693
    Prev
    Next
    INDEX
    Explanations

    which one to use?

    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
     Moreira
    0.38
     сани
    0.36
     नरम
    0.35
    排
    0.35
     सोच
    0.34
     xếp
    0.34
    play
    0.34
    Href
    0.33
     kesin
    0.33
    uh
    0.32
    POSITIVE LOGITS
     couples
    0.39
     (’
    0.35
    voegd
    0.35
     (^
    0.35
     ((
    0.34
     coupling
    0.34
    ించాలి
    0.34
     cavern
    0.33
     (\"
    0.33
    跏
    0.33
    Activations Density 0.005%

    No Known Activations