© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18028
    Prev
    Next
    INDEX
    Explanations

    howling wolves

    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_34_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
     rhiz
    0.41
     Acts
    0.40
    Acts
    0.40
     tropics
    0.38
     acts
    0.38
    块
    0.37
    稃
    0.36
     NRA
    0.36
     rhubarb
    0.35
     Atlantic
    0.35
    POSITIVE LOGITS
     wolves
    0.79
    🐺
    0.74
     Wolves
    0.70
     howling
    0.69
     werewolf
    0.68
     wolf
    0.64
    狼
    0.60
    wolves
    0.59
     howl
    0.58
    wolf
    0.55
    Activations Density 0.001%

    No Known Activations