© 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. 6986
    Prev
    Next
    INDEX
    Explanations

    words and phrases from technical question-answer scenarios

    oai_token-act-pair · gemini-2.0-flash

    variations of "I am"

    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
     I
    -0.65
    ]")]
    -0.63
    Diweddarwch
    -0.62
     GenerationType
    -0.58
    haustible
    -0.57
     esternos
    -0.54
     propOrder
    -0.54
    biamo
    -0.54
    temun
    -0.53
     मैंने
    -0.53
    POSITIVE LOGITS
     im
    2.09
     Im
    1.91
    Im
    1.84
     Ill
    1.57
    im
    1.52
     ill
    1.51
     IM
    1.48
    Ill
    1.36
     id
    1.34
     Id
    1.34
    Activations Density 9.768%

    No Known Activations