© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200761
    Prev
    Next
    INDEX
    Explanations

    reset index

    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_37_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
     zahl
    0.41
    욌
    0.40
     छव
    0.40
    vaccinated
    0.37
     Behaviour
    0.36
     zahlen
    0.36
    锈
    0.36
     Recovery
    0.36
    地下
    0.36
     Faso
    0.35
    POSITIVE LOGITS
    鮫
    0.43
     pressures
    0.38
     extrapolate
    0.37
    ዩ
    0.35
    DOI
    0.34
     Butterfly
    0.34
     Gau
    0.34
     soc
    0.33
    removeChild
    0.33
     quadrupole
    0.33
    Activations Density 0.000%

    No Known Activations