© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9067
    Prev
    Next
    INDEX
    Explanations

    continuationHIGHunderstandingRISK

    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_13_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
    ць
    0.62
     Cahill
    0.49
     workings
    0.48
     charts
    0.47
    ক
    0.47
     discontinuities
    0.46
     investigates
    0.46
    ruptcy
    0.46
     Bengali
    0.46
     restarts
    0.46
    POSITIVE LOGITS
    みたいな
    0.45
    仄
    0.45
    ोदर
    0.44
    sentiment
    0.44
     luego
    0.43
    োই
    0.43
    ̬
    0.43
     fuerza
    0.42
    ো
    0.42
    ার
    0.42
    Activations Density 0.000%

    No Known Activations