© 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. 8724
    Prev
    Next
    INDEX
    Explanations

    words related to dog ownership, training, and behavior

    oai_token-act-pair · gemini-2.0-flash

    dog training

    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
     виправивши
    -0.77
     препратки
    -0.67
    jsii
    -0.66
     estimés
    -0.66
    хьтан
    -0.63
    SequentialGroup
    -0.61
    ftagPool
    -0.61
    XtraEditors
    -0.58
     informée
    -0.58
    +#+#
    -0.58
    POSITIVE LOGITS
    reise
    0.51
     wobble
    0.47
     kele
    0.46
     wellness
    0.45
     intervene
    0.44
    urto
    0.43
     Dario
    0.43
    itto
    0.42
     نار
    0.42
     Visite
    0.42
    Activations Density 9.015%

    No Known Activations