© 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. 5831
    Prev
    Next
    INDEX
    Explanations

    words within scientific articles (particularly medical or biological) that are related to testing or experimentation

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    tagHelperRunner
    -0.76
    fromnode
    -0.71
     CreateTagHelper
    -0.70
    ướt
    -0.62
    ".
    -0.62
    PageRoute
    -0.61
    PyExc
    -0.61
     referenties
    -0.60
    swick
    -0.59
    ApiModelProperty
    -0.58
    POSITIVE LOGITS
    -
    0.59
    Filmografie
    0.51
     vitro
    0.49
     femei
    0.49
     vivo
    0.46
     platelets
    0.46
    bred
    0.45
    postmedia
    0.45
     situ
    0.44
     collagen
    0.44
    Activations Density 12.468%

    No Known Activations