© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214136
    Prev
    Next
    INDEX
    Explanations

    describing content as engaging

    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_16_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
    co
    0.44
    ти
    0.41
    for
    0.40
    asz
    0.39
     ဘ
    0.38
    })\
    0.36
    iru
    0.36
    lang
    0.36
     autre
    0.36
    T
    0.36
    POSITIVE LOGITS
    ানোর
    0.41
    itley
    0.40
    渽
    0.39
     functioned
    0.38
     NONCLUSTERED
    0.38
    addam
    0.38
     formulation
    0.38
     conspired
    0.38
     gestaltet
    0.38
     funcion
    0.38
    Activations Density 0.008%

    No Known Activations