INDEX

Explanations

verbs related to performing a calculation or process

oai_token-act-pair · gemini-2.0-flash

actions or processes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Hozzáférés

-0.65

oredCriteria

-0.63

LookAnd

-0.60

SequentialGroup

-0.57

 Pingback

-0.57

mehl

-0.55

phinx

-0.53

anggap

-0.52

CppMethod

-0.50

 onOptions

-0.50

POSITIVE LOGITS

StructEnd

0.75

 AssemblyCompany

0.46

OGND

0.45

KommentareTeilen

0.45

WebVitals

0.44

𓃵

0.44

 Nestor

0.43

ClientSize

0.42

 كومونز

0.41

principalColumn

0.41

Activations Density 0.384%

verbs related to performing a calculation or process

actions or processes

No Comments

No Known Activations