© 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. 32125
    Prev
    Next
    INDEX
    Explanations

    activity in comments

    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
    commander
    0.34
     અધિકારી
    0.34
    वेशन
    0.34
     বিদ্যা
    0.34
    ulator
    0.33
    ların
    0.33
    伦
    0.33
     imperio
    0.33
    கே
    0.33
     cantor
    0.33
    POSITIVE LOGITS
    raintes
    0.35
    poline
    0.34
     Vigo
    0.33
     moy
    0.33
     vina
    0.32
     Groundwater
    0.32
    cedures
    0.32
     vines
    0.32
     >>=
    0.32
    ләү
    0.31
    Activations Density 0.006%

    No Known Activations