INDEX

Explanations

statements of plans about what will be done

oai_token-act-pair · gemini-2.0-flash

will

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 définiti

-0.89

tagHelperRunner

-0.86

IntoConstraints

-0.86

 ProtoMessage

-0.84

OGND

-0.84

 Bioaccumulative

-0.73

AlterField

-0.73

MigrationBuilder

-0.73

ApiModelProperty

-0.71

 mourut

-0.71

POSITIVE LOGITS

:✨

0.49

 cost

0.46

let

0.43

 comprise

0.42

 include

0.42

cul

0.39

 cure

0.38

 open

0.37

be

0.37

 aren

0.37

Activations Density 2.385%

statements of plans about what will be done

will

No Comments

No Known Activations