© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41715
    Prev
    Next
    INDEX
    Explanations

    academic and technical terms

    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_22_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
    Storing
    0.41
    颜
    0.39
    Occ
    0.39
    Operating
    0.38
    Obes
    0.37
    应用于
    0.37
    Duty
    0.36
    ထိ
    0.36
    Yang
    0.36
    位
    0.36
    POSITIVE LOGITS
     ფედერ
    0.48
     geology
    0.44
    विला
    0.44
     peligro
    0.44
    helium
    0.44
     deras
    0.43
     представителей
    0.42
     dinero
    0.42
     sodio
    0.42
     dysplasia
    0.41
    Activations Density 0.000%

    No Known Activations