© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205110
    Prev
    Next
    INDEX
    Explanations

    young, marine, carpenter, whirlwind, quiet

    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_37_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
     अदर
    0.40
    㕕
    0.39
    苹
    0.36
     lags
    0.36
     የስ
    0.36
     Gett
    0.36
    roversial
    0.36
     её
    0.35
     lag
    0.35
    cepter
    0.35
    POSITIVE LOGITS
     recently
    0.47
     suspect
    0.42
     appena
    0.41
    proud
    0.41
     proud
    0.40
     baru
    0.39
    ⋅
    0.38
    encour
    0.38
     dutiful
    0.38
     just
    0.36
    Activations Density 0.010%

    No Known Activations