© 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. 49113
    Prev
    Next
    INDEX
    Explanations

    prior acts, complaint, notice

    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
     అమ
    0.38
    Titanic
    0.38
    Todo
    0.37
    ὖ
    0.37
    情况下
    0.36
     insecurity
    0.36
    ǎi
    0.35
     গ্রন্থ
    0.35
     Объ
    0.35
    odoro
    0.34
    POSITIVE LOGITS
    をも
    0.38
     indictment
    0.37
    --;
    0.37
    ocaine
    0.37
     fixation
    0.36
     cus
    0.36
     screws
    0.36
     group
    0.36
    belum
    0.36
     lp
    0.36
    Activations Density 0.005%

    No Known Activations