© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36033
    Prev
    Next
    INDEX
    Explanations

    probability density function

    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_31_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
    廢
    0.32
    废
    0.32
     rooted
    0.31
     decay
    0.31
    rooted
    0.31
    廃
    0.29
     rhetoric
    0.29
     recoverable
    0.29
    根
    0.29
    decay
    0.28
    POSITIVE LOGITS
     koordin
    0.38
     coordin
    0.32
     coordinador
    0.31
    konstru
    0.31
    iber
    0.31
     apartamentos
    0.30
    Province
    0.30
     Konstru
    0.30
     Province
    0.30
     constructed
    0.29
    Activations Density 0.018%

    No Known Activations