© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235307
    Prev
    Next
    INDEX
    Explanations

    hammer bang strike

    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_46_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
     hammer
    3.42
    Hammer
    3.20
     Hammer
    3.19
     hammers
    3.08
    hammer
    2.94
     hammered
    2.70
     hammering
    2.66
    锤
    2.58
     Hammers
    2.56
    鎚
    2.05
    POSITIVE LOGITS
     Akash
    0.42
     আর্কাইভ
    0.38
    Sew
    0.38
     রস
    0.37
     narr
    0.37
     Balkans
    0.36
     Charlotte
    0.36
     Agr
    0.36
     Socio
    0.36
     архів
    0.36
    Activations Density 0.007%

    No Known Activations