© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9567
    Prev
    Next
    INDEX
    Explanations

    words/phrases that indicate logical connections or comparisons are being made

    oai_token-act-pair · gemini-2.0-flash

    Agreement/affirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     CreateTagHelper
    -0.77
    __':
    -0.68
    addPreferredGap
    -0.68
    jména
    -0.68
    HostException
    -0.62
    BASEPATH
    -0.60
     conversely
    -0.58
    انجليز
    -0.58
    isissez
    -0.57
    basicConfig
    -0.57
    POSITIVE LOGITS
    fen
    0.47
    cl
    0.46
    KeySpec
    0.45
    fa
    0.45
    mes
    0.45
    λλ
    0.44
    racy
    0.44
    Fe
    0.44
    dbach
    0.44
    ⓘ
    0.44
    Activations Density 40.876%

    No Known Activations