© 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. 240188
    Prev
    Next
    INDEX
    Explanations

    numbers or size comparisons

    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
     uncle
    0.11
    BOTH
    0.11
     স্নেহ
    0.11
    VENT
    0.11
     pegged
    0.11
     prefixed
    0.10
    👱
    0.10
    IPT
    0.10
    EVERY
    0.10
    INDOW
    0.10
    POSITIVE LOGITS
    遴
    0.12
    mockito
    0.12
     vody
    0.12
     vendredi
    0.11
    ങ
    0.11
     Halloween
    0.11
     വിജയ
    0.11
     वर्षी
    0.11
    unda
    0.11
     Weekend
    0.11
    Activations Density 0.000%

    No Known Activations