INDEX

Explanations

code/numbers

np_max-act-logits · gemini-2.0-flash

equations, variables, or mathematical expressions

oai_token-act-pair · gemini-2.0-flash

code snippets

np_token-act-pair-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

 المعيارى

-0.57

setCenter

-0.55

érité

-0.53

 utafitiHapana

-0.53

 Retire

-0.52

 חיצוניים

-0.51

Referencie

-0.50

rition

-0.49

 retire

-0.49

DockStyle

-0.49

POSITIVE LOGITS

IUrlHelper

0.75

ScopeManager

0.61

parsedMessage

0.58

oredCriteria

0.57

 objectForKey

0.54



0.54

forName

0.54

GrantedAuthority

0.52

WebControls

0.51

SourceChecksum

0.50

Activations Density 1.566%

code/numbers

equations, variables, or mathematical expressions

code snippets

No Comments

No Known Activations