© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204148
    Prev
    Next
    INDEX
    Explanations

    climbing

    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_37_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
     climbing
    0.58
     climber
    0.54
     Climbing
    0.52
     Climb
    0.51
     climb
    0.50
     climbers
    0.50
    🧗
    0.47
     climbed
    0.45
     climbs
    0.44
     Boulder
    0.43
    POSITIVE LOGITS
    ilerden
    0.43
     seashore
    0.42
     hundred
    0.38
     बहादुर
    0.38
    isho
    0.38
     fifty
    0.37
    百
    0.37
    珹
    0.37
     beachfront
    0.36
     संविधान
    0.36
    Activations Density 0.002%

    No Known Activations