© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89273
    Prev
    Next
    INDEX
    Explanations

    ze

    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_60_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
    クト
    0.43
     menyel
    0.40
    ย
    0.39
     posX
    0.39
    𝔂
    0.38
     anek
    0.38
    儚
    0.37
     കേ
    0.37
     perceive
    0.37
    筝
    0.37
    POSITIVE LOGITS
    es
    0.60
    us
    0.60
    vent
    0.50
    ad
    0.48
    arlight
    0.47
    inschaft
    0.45
    Vent
    0.45
    esters
    0.45
    ivities
    0.44
    ificados
    0.44
    Activations Density 0.000%

    No Known Activations