© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218417
    Prev
    Next
    INDEX
    Explanations

    GAAP vs. EPS, pro forma amounts

    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_31_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
    㯎
    0.40
    拏
    0.39
     Vib
    0.39
    姮
    0.38
     टोक
    0.37
    䔉
    0.37
     Juliana
    0.37
     Gop
    0.36
    己
    0.35
     cac
    0.35
    POSITIVE LOGITS
     down
    0.38
     digested
    0.38
     banked
    0.37
     buried
    0.37
     mailing
    0.37
     freel
    0.37
    brows
    0.37
    ums
    0.37
    Joey
    0.36
     €
    0.35
    Activations Density 0.000%

    No Known Activations