© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reasoning and research

    oai_token-act-pair · gemini-2.0-flash

    technical abstract

    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
    bootstrapcdn
    -0.52
     C
    -0.52
    AnchorStyles
    -0.51
    vegas
    -0.51
     J
    -0.51
    kPa
    -0.51
    ->_
    -0.50
     Gators
    -0.50
     M
    -0.50
    zap
    -0.50
    POSITIVE LOGITS
    IUrlHelper
    0.64
     pleaſure
    0.62
     Majefty
    0.62
     Савезне
    0.60
    wiſe
    0.59
     Monfieur
    0.59
     chofe
    0.57
     ſtate
    0.56
     Efq
    0.56
    sterious
    0.55
    Activations Density 14.224%

    No Known Activations