© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10256
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to capability, possibility, planning, and prediction

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     able
    -2.00
     ability
    -1.59
     Ability
    -1.32
    Able
    -1.30
     Able
    -1.30
    Ability
    -1.27
     can
    -1.26
     pouvoir
    -1.24
    能够
    -1.23
     capable
    -1.20
    POSITIVE LOGITS
    PerformLayout
    0.79
     INTERESAR
    0.70
    Tikang
    0.64
    Hozzáférés
    0.62
    setVerticalGroup
    0.59
    aarrggbb
    0.59
     مؤرشف
    0.59
    endencias
    0.58
    TagMode
    0.55
     CreateTagHelper
    0.55
    Activations Density 2.347%

    No Known Activations