© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 823
    Prev
    Next
    INDEX
    Explanations

    words related to technology and communication

    oai_token-act-pair · gemini-2.0-flash

    computers and technology

    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
    utorial
    -0.56
     متعلقه
    -0.52
     SIMBAD
    -0.49
    Fitment
    -0.49
    aratus
    -0.49
    Crossref
    -0.47
     feveral
    -0.46
    hooter
    -0.46
    lihood
    -0.45
    춤
    -0.45
    POSITIVE LOGITS
    UnusedPrivate
    0.69
    +#+#
    0.62
    httphttps
    0.57
    ValueStyle
    0.56
    jsonwebtoken
    0.52
    thur
    0.52
    BufferException
    0.52
    adaptiveStyles
    0.51
     jsPsych
    0.49
     invokingState
    0.49
    Activations Density 6.398%

    No Known Activations