© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10006
    Prev
    Next
    INDEX
    Explanations

    content related to Raspberry Pi, microcontrollers, and related technology.

    oai_token-act-pair · gemini-2.0-flash

    computers/circuits

    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
     preſent
    -0.62
     fhew
    -0.61
    ValueStyle
    -0.60
     pleaſure
    -0.59
     neceff
    -0.59
    شهاد
    -0.58
    Vidite
    -0.57
     prefent
    -0.55
     caufe
    -0.55
     fometimes
    -0.55
    POSITIVE LOGITS
     utafitiHapana
    0.52
    internalType
    0.51
    ใ
    0.50
    (!__
    0.49
    </thead>
    0.47
    FieldBuilder
    0.47
    chera
    0.46
    govine
    0.45
    NewValue
    0.45
    UNITIES
    0.45
    Activations Density 12.912%

    No Known Activations