© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246082
    Prev
    Next
    INDEX
    Explanations

    screen setup

    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
     plufieurs
    0.45
     ክ
    0.44
     diminue
    0.43
     ಹುಡು
    0.42
     वस्तु
    0.41
     antennis
    0.40
     hitta
    0.40
     ಎರಡು
    0.39
    骸
    0.39
     diminu
    0.39
    POSITIVE LOGITS
    per
    0.39
    tick
    0.39
     Origins
    0.38
    ten
    0.37
    Origins
    0.36
     sights
    0.36
    Integr
    0.35
    integr
    0.35
     Happiness
    0.35
     glimps
    0.35
    Activations Density 0.000%

    No Known Activations