INDEX

Explanations

words related to possibility and intent

oai_token-act-pair · gemini-2.0-flash

non-english

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

 MainAxisSize

-0.71

__((

-0.70

 dAtA

-0.65

ValueGeneration

-0.64

twimg

-0.64

styleType

-0.64

Tazama

-0.63

 aDecoder

-0.63

MessageTagHelper

-0.59

 referrerpolicy

-0.59

POSITIVE LOGITS

elemField

0.59

덕

0.47

 médicaux

0.47

ømme

0.46

ymce

0.45

 autorytatywna

0.45

PRNewswire

0.45



0.45

rimi

0.45

 trava

0.45

Activations Density 5.801%

words related to possibility and intent

non-english

No Comments

No Known Activations