© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208468
    Prev
    Next
    INDEX
    Explanations

    Emer

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     gemeinsam
    0.42
     reducing
    0.40
     descending
    0.38
    웁
    0.38
     }+\
    0.38
     things
    0.38
     feral
    0.38
     MAKING
    0.38
     intangible
    0.37
     microorganism
    0.37
    POSITIVE LOGITS
    Changed
    0.43
    Disabled
    0.35
    ്യൂ
    0.35
     Avis
    0.34
    Uni
    0.34
     cheated
    0.34
     Changed
    0.34
    碛
    0.34
     সাড়ে
    0.33
     sintet
    0.33
    Activations Density 0.001%

    No Known Activations