INDEX

Explanations

news channels

oai_token-act-pair · gemini-2.0-flash

News and TV networks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

$_['

-0.47

 Institution

-0.44

TGF

-0.44

postsleuth

-0.43

addContainerGap

-0.43

poptosis

-0.42

 fibrosis

-0.41

 institution

-0.40

ug

-0.40

 stratification

-0.40

POSITIVE LOGITS

principalColumn

0.73

EndGlobalSection

0.66

PerformLayout

0.64

########.

0.63

PreExecute

0.63

RegressionTest

0.60

WireFormatLite

0.59

ReusableCell

0.59

 Taktlose

0.59

 GlobalKey

0.59

Activations Density 0.763%

news channels

News and TV networks

No Comments

No Known Activations