© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24017
    Prev
    Next
    INDEX
    Explanations

    able

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Expensive
    0.40
    expensive
    0.38
     विलय
    0.38
     struggle
    0.37
     erz
    0.37
     डेली
    0.36
     bif
    0.36
    苛
    0.36
     उर्फ
    0.36
     Expensive
    0.36
    POSITIVE LOGITS
    ás
    0.66
    ucho
    0.44
    á
    0.44
    ÁS
    0.43
    SpringMVCProject
    0.41
    able
    0.40
     disse
    0.39
    aacute
    0.39
    ondo
    0.38
    Á
    0.38
    Activations Density 0.045%

    No Known Activations