INDEX

Explanations

html and source code

oai_token-act-pair · gemini-2.0-flash

code snippets in angle brackets

np_token-act-pair-logits · gemini-2.0-flash

computer code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 باخ

-0.54

原始内容存档于

-0.50

 wür

-0.48

 Hyper

-0.48

Runner

-0.48

出版年

-0.47

runners

-0.47

amir

-0.47

 dấu

-0.46

 yếu

-0.46

POSITIVE LOGITS

SequentialGroup

0.71

PerformLayout

0.71

AndEndTag

0.69

SerializedSize

0.67

LookAnd

0.66

RenderAtEndOf

0.65

GEBURTSDATUM

0.64

NamedQuery

0.60

featureID

0.60

 onCancelled

0.59

Activations Density 0.680%

html and source code

code snippets in angle brackets

computer code

No Comments

No Known Activations