INDEX

Explanations

words related to medical issues, viruses or hospital acquired infections

oai_token-act-pair · gemini-2.0-flash

negative events

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

 accident

-0.80

RenderAtEndOf

-0.71

gap

-0.70

Accident

-0.70

accident

-0.70

 acidente

-0.66

 Incident

-0.66

 incident

-0.66

 ACCIDENT

-0.65

 Accident

-0.64

POSITIVE LOGITS

 utafitiHapana

0.74

 block

0.74

ρευ

0.60

 JpaRepository

0.59

#+#

0.55

 blow

0.53

mers

0.53

 touch

0.51

واده

0.51

IntoConstraints

0.50

Activations Density 4.701%

words related to medical issues, viruses or hospital acquired infections

negative events

No Comments

No Known Activations