© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220669
    Prev
    Next
    INDEX
    Explanations

    non-English names and scripts

    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
    𝗶
    0.43
    ဥ
    0.41
    鄀
    0.40
    ୮
    0.39
    者に
    0.38
     Wilkes
    0.38
    ")%>%
    0.37
    ="%
    0.37
     осіб
    0.37
    amending
    0.37
    POSITIVE LOGITS
     oscillate
    0.39
     stash
    0.37
     bypassed
    0.36
    matik
    0.36
    ycle
    0.36
    idum
    0.36
     breathes
    0.35
     raw
    0.34
    ष्णु
    0.34
    穹
    0.34
    Activations Density 0.001%

    No Known Activations