© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10945
    Prev
    Next
    INDEX
    Explanations

    language related to optics

    oai_token-act-pair · gemini-2.0-flash

    beam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Beam
    -1.02
     beam
    -0.93
    beam
    -0.84
    Beam
    -0.84
     beams
    -0.79
     BEAM
    -0.77
     wealth
    -0.76
    wealth
    -0.70
     Beams
    -0.69
    beams
    -0.69
    POSITIVE LOGITS
    <bos>
    1.11
    ’
    0.53
     her
    0.52
     насељу
    0.51
    География
    0.47
    Manbalar
    0.47
    NameInMap
    0.46
     structure
    0.45
    Népesség
    0.44
     hard
    0.44
    Activations Density 1.769%

    No Known Activations