© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2405
    Prev
    Next
    INDEX
    Explanations

    locations, schools and dates

    oai_token-act-pair · gemini-2.0-flash

    Names and external references

    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
    mobileqq
    -0.59
    ⓧ
    -0.57
     שוליים
    -0.57
     groupName
    -0.57
    that
    -0.55
    DOCTYPE
    -0.54
     appName
    -0.53
     Chrift
    -0.53
    #+#
    -0.53
    nestjs
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.58
    ']],
    0.58
    '):
    
    0.54
     is
    0.54
    "}},
    0.53
    ']));
    0.51
    "])
    
    0.50
    _))
    0.49
    }}},
    0.49
    '},
    
    0.49
    Activations Density 26.978%

    No Known Activations