INDEX

Explanations

words related to images, medical sensations, numerical values, and legal situations

oai_token-act-pair · gemini-2.0-flash

taking pictures/actions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

mybatisplus

-0.93

 AssemblyVersion

-0.85

findpost

-0.82

addGap

-0.81

 viewType

-0.79

'{@

-0.76

 BoxDecoration

-0.74

 MessageBoxIcon

-0.74

imageshack

-0.74

 HasFactory

-0.73

POSITIVE LOGITS

せ

0.50

an

0.47

Sil

0.46

ワイイ

0.45

Sil

0.45

kta

0.44

ίες

0.44

sil

0.44

ah

0.44

forme

0.44

Activations Density 1.460%

words related to images, medical sensations, numerical values, and legal situations

taking pictures/actions

No Comments

No Known Activations