© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7838
    Prev
    Next
    INDEX
    Explanations

    snippets of code with assignment operators and matrix usage

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
     CreateTagHelper
    -0.96
    __':
    -0.84
    makeConstraints
    -0.81
    AndEndTag
    -0.75
    tagHelperRunner
    -0.68
    __':
    -0.68
     Normdatei
    -0.67
    DockStyle
    -0.67
    AddTagHelper
    -0.66
    findpost
    -0.66
    POSITIVE LOGITS
    Földrajzportál
    0.46
     Genetic
    0.43
    Genetic
    0.42
    subseteq
    0.42
    lethal
    0.42
     Quantitative
    0.41
     genetic
    0.41
    essay
    0.41
     lang
    0.40
    цвета
    0.40
    Activations Density 30.706%

    No Known Activations