INDEX

Explanations

code snippets, potentially PHP or Python, involving database or GPIO access using a "relay" identifier.

oai_token-act-pair · gemini-2.0-flash

underscore

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Therapeutics

-0.67

-0.52

 Technologies

-0.51

-0.48

 Oils

-0.48

-0.47

ühner

-0.47

 Architects

-0.47

 Bridges

-0.46

 Homes

-0.46

POSITIVE LOGITS

出版年

0.75

featureID

0.73

path

0.64

id

0.63

fromnode

0.61

face

0.60

brand

0.59

ⓧ

0.59

trend

0.59

tvguidetime

0.59

Activations Density 20.758%

code snippets, potentially PHP or Python, involving database or GPIO access using a "relay" identifier.

underscore

No Comments

No Known Activations