© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203811
    Prev
    Next
    INDEX
    Explanations

    age problems with family members

    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_25_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
     made
    0.39
    脚
    0.38
    arantee
    0.38
    щен
    0.36
     depicted
    0.36
    mluv
    0.36
     =>
    0.36
     framed
    0.36
     pictures
    0.35
    omin
    0.35
    POSITIVE LOGITS
     उठता
    0.40
     వివిధ
    0.39
    itesi
    0.39
     enfermed
    0.38
    GREES
    0.37
    㐰
    0.37
     Married
    0.37
    벍
    0.36
     boon
    0.36
     저희
    0.35
    Activations Density 0.001%

    No Known Activations