INDEX

Explanations

phrases related to seeking medical advice

oai_token-act-pair · gemini-2.0-flash

medical advice

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

UnusedPrivate

-0.60

WithIdentifier

-0.54

ScopeManager

-0.54

 autorytatywna

-0.53

 JpaRepository

-0.52

TagMode

-0.47

ApiModelProperty

-0.47

hamilan

-0.46

 CURIAM

-0.46

 ProtoMessage

-0.45

POSITIVE LOGITS

fjspx

0.58

 Italijani

0.57

zzar

0.55

 Baillargeon

0.54

OwnProperty

0.54

/*---

0.54

الإنجليزية

0.54

 authorised

0.52

 someone

0.52

niejs

0.51

Activations Density 3.490%

phrases related to seeking medical advice

medical advice

No Comments

No Known Activations