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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    variable names plus related math and electronics terms

    oai_token-act-pair · gemini-2.0-flash

    Vin/Vo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     VA
    -0.96
     Va
    -0.87
    Va
    -0.76
    VA
    -0.74
     VC
    -0.73
     va
    -0.71
     vc
    -0.71
    VC
    -0.71
    VP
    -0.70
    <bos>
    -0.68
    POSITIVE LOGITS
     Roskov
    0.73
    ########.
    0.73
     CreateTagHelper
    0.69
     ***!
    0.68
    WriteAttribute
    0.68
    Tikang
    0.65
    +:+
    0.64
    Espèce
    0.63
    ruptedException
    0.59
    #+#
    0.59
    Activations Density 4.732%

    No Known Activations