INDEX

Explanations

words related to medical research and commercial apps/marketability.

oai_token-act-pair · gemini-2.0-flash

scientific research

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

"])

-0.76

EndContext

-0.64

StoryboardSegue

-0.63

)");

-0.61

asgi

-0.59

"]);

-0.58

 onAnimation

-0.58

"]/

-0.57

 unknownFields

-0.57

 nahilalakip

-0.57

POSITIVE LOGITS

tig

0.70

td

0.64

tige

0.60

tp

0.60

tor

0.60

tador

0.59

TN

0.57

TPP

0.57

 Titans

0.56

tyk

0.56

Activations Density 13.449%

words related to medical research and commercial apps/marketability.

scientific research

No Comments

No Known Activations