© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86630
    Prev
    Next
    INDEX
    Explanations

    explaining mechanisms

    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_18_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
    Like
    0.26
    irce
    0.26
    ḗ
    0.25
    私は
    0.24
    我会
    0.24
     люблю
    0.24
     Cullen
    0.24
     quên
    0.24
    几次
    0.24
    ExpNow
    0.24
    POSITIVE LOGITS
     cases
    0.28
     computers
    0.28
     formats
    0.25
    ;//
    0.24
     infos
    0.24
     osoby
    0.24
     grantor
    0.24
     her
    0.24
     format
    0.24
     aliens
    0.23
    Activations Density 0.004%

    No Known Activations