INDEX

Explanations

definitions, implementations, or declarations

oai_token-act-pair · gemini-2.0-flash

{

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 CreateTagHelper

-0.77

matchCondition

-0.54

Fund

-0.50

fund

-0.48

 Funds

-0.46

 Fund

-0.46

 shunt

-0.45

DebuggerStep

-0.45

TagMode

-0.45

ang

-0.44

POSITIVE LOGITS

0.83

ThroughAttribute

0.71

\{\\

0.66

 мәкал

0.61

enderror

0.60

ADELPHIA

0.57

Conclusie

0.57

IsMutable

0.56

}{*}{}

0.56

 протя

0.54

Activations Density 0.136%

definitions, implementations, or declarations

{

No Comments

No Known Activations