© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206692
    Prev
    Next
    INDEX
    Explanations

    width and height aspect ratio

    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_20_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
    PatientR
    0.47
     కలిసి
    0.45
     جیل
    0.44
    რც
    0.44
    KSprite
    0.43
    尝
    0.43
     بھی
    0.43
    ເພ
    0.43
    PluginResult
    0.43
    relationships
    0.42
    POSITIVE LOGITS
     जैसे
    0.44
     Purchasing
    0.42
     ul
    0.39
    scalar
    0.39
     spô
    0.39
     způso
    0.39
     ideales
    0.39
     rigidity
    0.39
    ū
    0.39
    UES
    0.38
    Activations Density 0.000%

    No Known Activations