© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212144
    Prev
    Next
    INDEX
    Explanations

    hair and hairstyles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     стро
    0.38
     OpenAI
    0.37
    켜
    0.37
     मिनि
    0.37
     corto
    0.36
     Pis
    0.36
    TxtArea
    0.36
     כן
    0.36
    响
    0.35
    リティ
    0.35
    POSITIVE LOGITS
     hair
    2.56
    Hair
    2.36
     Hair
    2.34
    hair
    2.27
     HAIR
    2.16
    髪
    2.05
     haird
    2.02
     hairstyle
    1.97
     hairstyles
    1.96
    ヘア
    1.92
    Activations Density 0.002%

    No Known Activations