© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208715
    Prev
    Next
    INDEX
    Explanations

    comprised, materials, unitary, architecture

    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_19_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
    ్రే
    0.34
     прадстаў
    0.32
     Riga
    0.31
     wiss
    0.31
    ե
    0.31
     Risks
    0.31
     Darryl
    0.31
     Australia
    0.30
     esperienze
    0.30
     Risk
    0.30
    POSITIVE LOGITS
    ゆる
    0.29
     consonants
    0.29
     consonant
    0.29
     interf
    0.29
    fff
    0.28
     unitary
    0.28
     vibrant
    0.28
    forward
    0.28
    任意の
    0.28
    당
    0.27
    Activations Density 0.001%

    No Known Activations