© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    common short words such as pronouns, helping verbs, prepositions, and articles

    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_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
    StoryboardSegue
    -0.77
    AutoScaleMode
    -0.74
    AddTagHelper
    -0.71
    ніципалі
    -0.64
    SourceChecksum
    -0.63
    GraphicsUnit
    -0.62
    UnknownFieldSet
    -0.61
    MemoryWarning
    -0.61
    BufferException
    -0.60
    VIA
    -0.58
    POSITIVE LOGITS
    "}}>
    0.60
    }}>
    0.59
     si
    0.59
    )}>
    0.58
    <>();
    0.57
    '>
    0.56
    }>
    0.55
     }}>
    0.55
    '}}>
    0.55
    发表于
    0.49
    Activations Density 0.255%

    No Known Activations