© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14622
    Prev
    Next
    INDEX
    Explanations

    German text containing references and quotations, especially regarding abstract concepts of permission and possibility.

    oai_token-act-pair · gemini-2.0-flash

    diverse text

    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
     the
    -2.53
    the
    -1.13
    ofthe
    -0.98
    tothe
    -0.92
     ofthe
    -0.88
    rethe
    -0.86
    The
    -0.84
     The
    -0.82
    OfThe
    -0.80
    nthe
    -0.73
    POSITIVE LOGITS
    ########.
    0.63
    ❋
    0.56
    Pyx
    0.52
     de
    0.50
    RTCK
    0.47
     DIE
    0.46
     виправивши
    0.45
     den
    0.45
     đó
    0.45
    multicolumn
    0.44
    Activations Density 0.233%

    No Known Activations