© 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. 242229
    Prev
    Next
    INDEX
    Explanations

    goal setting

    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
    accharide
    0.41
    噬
    0.39
    ypter
    0.38
    謊
    0.38
    AndroidManifest
    0.37
    subtree
    0.36
     przech
    0.35
    aggable
    0.34
    inte
    0.33
     धा
    0.33
    POSITIVE LOGITS
     orientated
    0.42
     orientation
    0.41
     CBP
    0.41
     oriented
    0.40
    ˈ
    0.40
     engagement
    0.40
     tuning
    0.40
     address
    0.39
     ADDRESS
    0.38
     overd
    0.38
    Activations Density 0.001%

    No Known Activations