© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3168
    Prev
    Next
    INDEX
    Explanations

    objective-c code related to decoding objects

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    __":
    -0.68
    _
    -0.63
    __':
    -0.63
    '],
    -0.61
    kháu
    -0.60
    '},
    -0.60
    .}~\
    -0.60
    )++;
    -0.60
    SOLD
    -0.59
    indrical
    -0.59
    POSITIVE LOGITS
    WireFormatLite
    0.59
    EventQueue
    0.48
    yntaxException
    0.48
    Tracce
    0.47
     кӀ
    0.45
    newtheorem
    0.44
    ծ
    0.44
    حياتها
    0.43
    حياته
    0.41
    计
    0.41
    Activations Density 6.074%

    No Known Activations