© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170010
    Prev
    Next
    INDEX
    Explanations

    stake and feed

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     vamp
    1.79
     vampire
    1.77
     Vampire
    1.63
     Vamp
    1.57
     vampires
    1.56
     Dracula
    1.06
     werewolf
    0.96
    🧛
    0.88
     zombie
    0.57
     Gothic
    0.55
    POSITIVE LOGITS
     staked
    0.63
     stakes
    0.61
     feeding
    0.56
     feedings
    0.54
     stake
    0.53
     staking
    0.52
     feed
    0.50
     sparkle
    0.50
    feeding
    0.48
     Stakes
    0.48
    Activations Density 0.002%

    No Known Activations