© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82794
    Prev
    Next
    INDEX
    Explanations

    increasing when conditions

    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_29_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
     ‘
    0.35
     breadth
    0.32
     Whirl
    0.31
     मगर
    0.29
     rectangle
    0.29
     streamline
    0.29
     '+'
    0.29
     nothing
    0.29
     waterfall
    0.29
     inlets
    0.29
    POSITIVE LOGITS
    Howard
    0.32
    Paused
    0.31
    }_{-
    0.30
    Oregon
    0.29
     Harding
    0.29
    Harrison
    0.29
    黼
    0.29
    Robinson
    0.28
    PRESSED
    0.28
    தீ
    0.28
    Activations Density 0.005%

    No Known Activations