INDEX

Explanations

code snippets containing variable names and data types

oai_token-act-pair · gemini-2.0-flash

programming code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

her

-0.47

 herself

-0.46

 оригіналу

-0.43

 adipis

-0.43

bas

-0.40

 JOIN

-0.40

 seek

-0.40

vol

-0.39

 fray

-0.39

wegg

-0.39

POSITIVE LOGITS

 مرئيه

0.76

]--;

0.68

TintMode

0.68

 Shakspeare

0.65

__":

0.65

 særlig

0.63

__':

0.63

 følgende

0.63

RegistryLite

0.63

 varandra

0.63

Activations Density 17.278%

code snippets containing variable names and data types

programming code

No Comments

No Known Activations