© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14911
    Prev
    Next
    INDEX
    Explanations

    forms of 'have' and 'been' verbs

    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_15_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
    р
    0.77
    ר
    0.64
     procrastination
    0.62
     mats
    0.61
     semper
    0.59
     hyperfine
    0.59
     pouches
    0.59
     mags
    0.59
     cyborg
    0.58
     papill
    0.58
    POSITIVE LOGITS
     Been
    0.84
    Been
    0.81
    been
    0.80
     been
    0.79
     BEEN
    0.67
    }{
    0.67
    }=\
    0.59
    eln
    0.59
    '};
    0.59
     الطريق
    0.58
    Activations Density 0.097%

    No Known Activations