© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32652
    Prev
    Next
    INDEX
    Explanations

    counts and calculations

    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_40_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
    Quaternion
    0.43
     Legend
    0.37
     scavenger
    0.36
    купно
    0.36
    Vocabulary
    0.36
    倾
    0.36
    કમ
    0.36
    او
    0.35
    RangeException
    0.35
    小物
    0.35
    POSITIVE LOGITS
     installs
    0.40
     frecuencias
    0.40
     selections
    0.39
    𝐱
    0.38
     x
    0.38
     failures
    0.37
    Freq
    0.37
    observer
    0.36
     Lass
    0.36
    トキ
    0.36
    Activations Density 0.070%

    No Known Activations