© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5116
    Prev
    Next
    INDEX
    Explanations

    cleaning, scrubbing, grime, dirt

    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
    acterium
    0.44
     infección
    0.38
    cessor
    0.37
    unused
    0.36
    Stephen
    0.36
    த்துவ
    0.36
    Ȧ
    0.35
    خص
    0.35
     PYTHON
    0.34
    ód
    0.34
    POSITIVE LOGITS
     Sabrina
    0.46
     WALK
    0.45
    锑
    0.43
     applied
    0.42
     dirt
    0.41
     SB
    0.40
     оку
    0.40
     Scrub
    0.40
     Clan
    0.39
     appliquer
    0.39
    Activations Density 0.045%

    No Known Activations