INDEX

Explanations

words related to statistical analysis and research

oai_token-act-pair · gemini-2.0-flash

Probability and sampling

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

افية

-0.47

 Patience

-0.40

lao

-0.39

 Vall

-0.39

lao

-0.39

enderror

-0.38

 unofficial

-0.37

tiary

-0.37

acci

-0.37

syp

-0.37

POSITIVE LOGITS

 design

0.69

حوالہ

0.69

FormTagHelper

0.69

StructEnd

0.69

 Савезне

0.69

IUrlHelper

0.68

enterOuterAlt

0.67

 oprot

0.66

Portail

0.65

Viited

0.65

Activations Density 2.333%

words related to statistical analysis and research

Probability and sampling

No Comments

No Known Activations