INDEX

Explanations

words about actions and information relating to those actions.

oai_token-act-pair · gemini-2.0-flash

support

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

LayoutStyle

-0.62

NameInMap

-0.62

stateProvider

-0.61

BufferException

-0.53

ModelAdmin

-0.53

via

-0.53

อย่างไร

-0.52

 مواليد

-0.52

:+:

-0.52

 AttributeSet

-0.51

POSITIVE LOGITS

RTN

0.54

prüche

0.52

ICALS

0.51

deau

0.50

jao

0.50

]]]

0.49

findpost

0.49

gener

0.49

ayu

0.48

béco

0.47

Activations Density 3.481%

words about actions and information relating to those actions.

support

No Comments

No Known Activations