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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5161
    Prev
    Next
    INDEX
    Explanations

    technical explanations involving angles, especially in relation to antennas or optics.

    oai_token-act-pair · gemini-2.0-flash

    orientation viewed angles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     orientation
    -0.68
    utnik
    -0.61
     orientations
    -0.61
     angle
    -0.59
     ORIENT
    -0.58
    orientation
    -0.58
     angles
    -0.58
    ActionEvent
    -0.56
     AssemblyCulture
    -0.56
     orient
    -0.56
    POSITIVE LOGITS
    abestanden
    0.61
     виправивши
    0.55
    ScopeManager
    0.53
    Hochspringen
    0.49
    szám
    0.48
    각주
    0.48
    fromnode
    0.48
    iações
    0.47
    oporosis
    0.46
    Referencie
    0.46
    Activations Density 5.058%

    No Known Activations