INDEX

Explanations

proper nouns as well as publications and communicators

oai_token-act-pair · gemini-2.0-flash

News sources

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__':

-0.85

__":

-0.84

]")]

-0.84

 Exactos

-0.83

 initComponents

-0.83

 kasarigan

-0.81

 jsPsych

-0.79

HideFlags

-0.79

 MongoClient

-0.77

IsMutable

-0.77

POSITIVE LOGITS

Extra

0.40

 variable

0.39

 Danmark

0.36

{}{}

0.36

 magazine

0.35

leyici

0.34

jstor

0.34

<strong>

0.33

↵↵

0.33

できた

0.33

Activations Density 1.962%

proper nouns as well as publications and communicators

News sources

No Comments

No Known Activations