© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical sensations or body parts, particularly when the subject is feeling or experiencing something

    oai_token-act-pair · gemini-2.0-flash

    body, sex, violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.83
     متعلقه
    -0.77
    IsMutable
    -0.76
     myſelf
    -0.71
     Efq
    -0.67
    libft
    -0.66
    CodedInputStream
    -0.64
     becauſe
    -0.63
     Anſ
    -0.60
     themſelves
    -0.59
    POSITIVE LOGITS
     Réponses
    0.53
    éez
    0.51
    íslu
    0.50
     Entsch
    0.45
     hi
    0.44
    脚注の使い方
    0.44
     sain
    0.44
     hoi
    0.43
     per
    0.42
    határoz
    0.42
    Activations Density 1.370%

    No Known Activations