INDEX

Explanations

code snippets related to data encoding

oai_token-act-pair · gemini-2.0-flash

code related contexts

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

MessageTagHelper

-0.62

 мәкал

-0.55

ulemon

-0.53

Демографія

-0.53

 Meksiku

-0.52

 <=",

-0.52

 للاسماء

-0.50

 gepubliceerd

-0.49

 >=",

-0.46

 kasarigan

-0.45

POSITIVE LOGITS

providedIn

0.62

lapi

0.57

ContentLoaded

0.56

HostException

0.56

 realist

0.55

 realism

0.54

OptionsMenu

0.52

ferent

0.52

 specchio

0.52

diğ

0.52

Activations Density 5.209%

code snippets related to data encoding

code related contexts

No Comments

No Known Activations