© 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. 1464
    Prev
    Next
    INDEX
    Explanations

    text related to skills and abilities, especially clear and critical thinking around writing, ideas, and arguments

    oai_token-act-pair · gemini-2.0-flash

    language and clarity

    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
    #
    -0.69
    Multiline
    -0.55
     doGet
    -0.53
    ground
    -0.50
     оригіналу
    -0.48
    клопе
    -0.48
    bustion
    -0.48
    Mai
    -0.47
     dok
    -0.47
    lite
    -0.46
    POSITIVE LOGITS
     Efq
    0.81
    ConstraintMaker
    0.70
    Datuak
    0.64
    ſelf
    0.61
    EndInit
    0.60
     Houſe
    0.58
     doubtnut
    0.58
     myſelf
    0.57
    rungsseite
    0.56
    InputModule
    0.56
    Activations Density 8.208%

    No Known Activations