© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126034
    Prev
    Next
    INDEX
    Explanations

    Kwasi Akuffo, Kv7 platform, pis, apine

    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_3_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
    (
    0.84
    érieures
    0.80
    प्टन
    0.65
     fanfare
    0.64
    meleri
    0.64
     pertains
    0.63
     générales
    0.63
     pais
    0.63
     touted
    0.63
    らが
    0.63
    POSITIVE LOGITS
    ك
    0.64
    ת
    0.59
    ী
    0.58
    ก
    0.58
     It
    0.57
    מל
    0.57
    庥
    0.54
    ENDER
    0.54
     it
    0.53
     Ethiopia
    0.53
    Activations Density 0.000%

    No Known Activations