© 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. 7081
    Prev
    Next
    INDEX
    Explanations

    the letter "i" when it is not part of a word

    oai_token-act-pair · gemini-2.0-flash

    Medical research

    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
    expandindo
    -0.73
    findpost
    -0.71
    RenderAtEndOf
    -0.68
    లాలు
    -0.66
    Билгалдахарш
    -0.60
     aguacate
    -0.57
    曖昧さ回避
    -0.56
    swire
    -0.55
    galus
    -0.55
     Privacidade
    -0.53
    POSITIVE LOGITS
    phazard
    0.52
    optarg
    0.51
    uge
    0.50
    AppMethodBeat
    0.49
    accia
    0.47
    ulon
    0.46
     Sa
    0.45
     StringTokenizer
    0.45
    ain
    0.44
    DAOImpl
    0.44
    Activations Density 0.447%

    No Known Activations