© 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. 14991
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    Computer code

    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
    ंदीखरीदारी
    -0.59
    WaitGroup
    -0.59
     fVar
    -0.57
    IEN
    -0.57
    ContentAsync
    -0.56
    IER
    -0.54
    rasa
    -0.53
    ApiModelProperty
    -0.53
     Henley
    -0.53
    ConstraintMaker
    -0.52
    POSITIVE LOGITS
     anteced
    0.45
    нодоро
    0.44
     ced
    0.44
    edade
    0.43
     mío
    0.42
     cada
    0.42
    adec
    0.42
    Deadline
    0.42
    エコ
    0.41
     debilidad
    0.41
    Activations Density 2.540%

    No Known Activations