INDEX

Explanations

parts of the text that refer to a source or citation

oai_token-act-pair · gemini-2.0-flash

say "-"

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

InSection

-0.75

featureID

-0.72

StoryboardSegue

-0.71

NUMX

-0.69

 InputDecoration

-0.68

CCS

-0.67

 BorderRadius

-0.66

IsMutable

-0.64

ALA

-0.62

sizeCache

-0.62

POSITIVE LOGITS

 poil

0.45

gpl

0.43

 network

0.40

 кон

0.40

}"

0.40

)-

0.40

']

0.40

</h3>

0.39

</b>

0.39

</i>

0.39

Activations Density 14.594%

parts of the text that refer to a source or citation

say "-"

No Comments

No Known Activations