© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168424
    Prev
    Next
    INDEX
    Explanations

    childlike or infantile themes

    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_34_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
     asbestos
    0.38
     gold
    0.37
     demons
    0.37
     organs
    0.36
    Yves
    0.36
     পিছ
    0.35
    砻
    0.35
     jet
    0.35
     muff
    0.35
     zł
    0.35
    POSITIVE LOGITS
     childish
    1.64
     childlike
    1.59
     дет
    1.42
     детский
    1.38
     infantil
    1.37
    儿童
    1.28
    童
    1.26
    兒童
    1.25
     infantile
    1.24
     Infantil
    1.23
    Activations Density 0.096%

    No Known Activations