© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238202
    Prev
    Next
    INDEX
    Explanations

    actual bill amount

    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_25_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
     A
    0.39
     a
    0.39
     T
    0.37
     Heck
    0.37
     t
    0.36
     E
    0.36
     S
    0.36
     Meer
    0.36
     Therm
    0.36
     AL
    0.35
    POSITIVE LOGITS
     dosages
    0.40
    してもら
    0.37
     articulating
    0.37
    lsulfanyl
    0.36
    舞台
    0.36
     लाभार्थी
    0.36
     sulphuric
    0.35
    <unused985>
    0.35
    راہیم
    0.35
     seasonings
    0.35
    Activations Density 0.000%

    No Known Activations